Kimi-K3 on HuggingFace
11 hours ago (huggingface.co)
Related: Kimi-K3 Technical Report [pdf] - https://news.ycombinator.com/item?id=49070985
11 hours ago (huggingface.co)
Related: Kimi-K3 Technical Report [pdf] - https://news.ycombinator.com/item?id=49070985
This will be interesting for a few reasons. First, depending on where the median pricing settles w/ 3rd party providers will tell us what it costs to serve a 3T model. Since it's going to be mxfp4 native, it'll take ~1.5TB of VRAM to host this, which is juuust at the limit of 8xb200s (but realistically you'll need 16x for context / throughput optimisation). Won't be cheap to host, but at least we should get some range of $/MTok for a 3T model. Then we'll be able to guesstimate if "labs are subsidising tokens on API pricing".
Also interesting to see what effort it will take to fine-tune this beast. The latest AISI benchmarks on cybersec place it above glm5.2, but still way way behind SotA closed models. Some fine-tuning might be needed here. Also, interesting to see if Cursor does another training round on it, to directly compare it w/ kimi2.6/2.7 fine-tunes (composer series) and grok4.5.
Also also, interesting to see if someone takes on distilling (proper distillation, w/ training the entire distribution) from this into smaller models. (dsv4-kimi should be really good, since dsv4 is very cheap to serve)
It will be very interesting to see what kind of 'slow' performance people get from running it on a no GPU, but tons of RAM server (like a dual or quad socket xeon with 1.5 to 3TB of RAM). For the purpose of giving it longer duration tasks to generate a piece of something and come back and check on what it has done in 4 or 6 hours. Even if the output is like 5-6 tok/s, that might be usable for some purposes.
Huge price difference in what you can do with buying a used 4U rackmount server and putting 3TB of RAM in it (64GB DIMMs x quantity 32 in a quad socket xeon, you can see some benchmark prices on eBay for sets of 16 or 32 matched 64GB ECC DIMMs) for <$30,000, vs the cost of trying to run it on real GPU hardware.
Now obviously, as of the time I write this, the full precision hasn't been released nor has anyone like unsloth run it through quantization yet to produce a "Q8" or "Q8-XL" variant of it. But I think it's going to need more than 1536GB of RAM, with a usable and large amount of context, more like 2TB and preferably 2.5 to 3TB.
I also predict that people who try to run it in Q4 and Q6 will get the worst of both worlds, less precision/lost knowledge but also not reliable output that comes out too slow. In my personal opinion if I'm going to deal with something that is smart but slow and running on limited budget hardware, I need it to be Q8.
As you already went through the thought exercise of laying all this RAM over various slots, then match against the right CPU (which also you'll need multiple) - it becomes clear quite fast that it's trying to mimic the architecture of a GPU except in extremely low fidelity and bandwidth @ a higher energy cost.
> Even if the output is like 5-6 tok/s, that might be usable for some purposes.
You'll spend ~100x more on electricity than the API cost to have it run on someone else's GPU at several hundred tokens per second.
I think some sort of extreme data privacy requirement is the only situation that justifies this, but the intersection of {needs absolute data privacy, needs to run SOTA model, cannot afford GPUs} is really really narrow. I wouldn't be surprised if this is an empty set.
51 replies →
I dunno, K3 thinks a lot before it actually replies, and you might be in the ~1 tok/speed region or even "seconds / tokens", and with K3, you'd wait days if not weeks for a reply in that case.
Don't get me wrong, slow is sometimes better than "not at all", but depending on the performance, it might end up way too slow to even work for batched/async jobs like that.
3 replies →
They are saying that AMD's new Epyc Venice CPU has 16 memory channels allowing up to 1.6Tb/s of bandwidth. Which is higher bandwidth than most non-HBM GPUs.
So full CPU local AI inference may become viable option in coming years.
2 replies →
> running it on a no GPU, but tons of RAM server
Or from SSD using something like Colibri[1]. Not going to be quick, but at least runable.
[1]: https://github.com/JustVugg/colibri
5 replies →
> But I think it's going to need more than 1536GB of RAM, with a usable and large amount of context, more like 2TB and preferably 2.5 to 3TB.
The model is known to be MXFP4 according to Kimi's release blog post, so the model weights will be less than 1536GB: https://www.kimi.com/blog/kimi-k3
Also, their previous models were native INT4, so it would be weird if they went larger now.
1 reply →
> Even if the output is like 5-6 tok/s
On a 3T model I’d imagine you’d be closer to 0.05 tks
4 replies →
Those old LTT videos of high core-count threadrippers running GPU benchmarks become more relevant each day.
4 replies →
AISI is capped at 100M tokens and K3 is less token efficient than Anthropic/OpenAI models. There is an argument to be made, looking at AISI results, that with uncapped tokens it would be just slightly behind the closed weight players.
Speaking of finetune, currently a common practice is LoRA over bnb 4-bit base model, but I think it's time to replace bnb with GGUF as the base model format. GGUF is actively supporting new model architectures and more aggressive quantizations.
I've made some proof of concept in https://github.com/woct0rdho/transformers5-qwen3.5-recipe . We can finetune Qwen3.5-35B-A3B in 16 GiB VRAM, and DeepSeek-V4-Flash (284B-A13B) in 90 GiB VRAM, without CPU offload. This works well on unified memory machines like Strix Halo.
Even so, larger models like Kimi-K3 still require multiple GPUs and nodes, and there are a lot more to do compare to single-GPU training.
I dont quite understand why GGUF is better optimized. Are the performances better for the same amount of VRAM ?
1 reply →
I cannot be sure what the likes of Cursor have done, but I think it's incredibly unlikely that they have trained a QLoRA for Composer.
It's almost certainly full parameter post training of the original model weights.
> Then we'll be able to guesstimate if "labs are subsidising tokens on API pricing".
No, you don't. Without training cost you can infer only the marginal cost of serving this kind of models.
Moreover, you don't know the actual size of closed models (what if Fable is a 10T model? What if it's 1T?)
> No, you don't. Without training cost you can infer only the marginal cost of serving this kind of models.
Still useful; "are the labs marginally profitable just on the marginal inference costs?" is still a useful question to answer. After all, if they aren't even profitable on inference in isolation, then we can expect to see large price increases.
If they are able to turn a marginal profit on inference alone, then perhaps the price increases won't be so severe (or perhaps they expand the time between generations so that they spend less on training but take longer to complete training).
"Are the labs profitable at all?" is, of course, a much more useful question, but that doesn't mean that the first question is completely useless.
6 replies →
> Without training cost you can infer only the marginal cost of serving this kind of models.
Which is by far the most interesting number of the two.
> Moreover, you don't know the actual size of closed models (what if Fable is a 10T model? What if it's 1T?)
If you get close in output quality, then does that matter?
5 replies →
Training cost is directly impacted by inference cost nowadays. Most of the gains come from RL these days, and that is highly dependant on inference (~7:1 inference:training in units of compute). That's mainly because you want many roll-outs for each training scenario.
Of course inference efficiency is dictated by model architecture, size, etc. You can still guesstimate some of those and have an idea about cost/serve at several size tiers.
2 replies →
Gross margins are insanely important, possibly the most important single metric if for some reason you were forced to choose one.
2 replies →
>No, you don't. Without training cost you can infer only the marginal cost of serving this kind of models.
Are you talking about Kimi's training cost or the training cost of the model(s) that Kimi distilled?
Because Moonshot didn't even incur the majority of the training costs either
2 replies →
Since the model is natively MXFP4, I think it'll be even more interesting on the hardware front. It'll comfortably fit on a 8x AMD MI355X node. I suspect that'll drive token prices down, further.
Say a single Kimi K3 is deployed on 16 x B200s: how many concurrent users can that handle? I realize the question assumes a major simplification that everyone's prompts/sessions are the same.
>I realize the question assumes a major simplification that everyone's prompts/sessions are the same.
well, exactly.
that's tough to answer without just average sampling because some users will ask the model "what's todays date" or "what color is the sky?" and some users will ask "Let's rewrite the linux kernel in brainfuck."
You're assuming inference providers are going to sell tokens at cost. You're also assuming that the inference providers have will optimized inference engine. I haven't seen that to be the case so far, to be honest.
Take a look at GLM 5 vs GLM 5.2 pricing -- GLM 5.2 cost more despite being the same model.
Take a look a look at DeepSeek, which hosts DS v4, profitably, yet others aren't able or willing to match the price.
I'll be honest, I typed that message while having morning coffee, so it's just a quick reaction from my part, not a heavily researched article in a journal :)
But I do think that the median price where this settles will tell us something about the floor at which it is profitable to serve this model.
> DeepSeek, which hosts DS v4, profitably
I specifically mentioned 3rd party providers, because there can be an argument that model creators themselves are subsidising tokens to gather training data for the next model. In fact, ds are public about their gathering of data (at least on openrouter they're marked as such). So that 0.x price point for dsv4-pro is likely subsidised.
2 replies →
Xioami's MiMo did match DS-V4's price, although we now know that DeepSeek set their pricing lower than they could have, due to the leaked memo, and simply decided to use "10 months to recover capex" as their yardstick. Interestingly "10 months to recover capex" is also the same price SpaceX is renting space to Anthropic and Google for.
I think it's unclear the the DS hosted prices are profitable. AFAIK that haven't claimed that.
OTOH, the multiple providers who have settled around the same price point ($3.48/M output tokens for multiple providers with good reputations) does indicate where it is profitable: https://openrouter.ai/deepseek/deepseek-v4-pro#providers
If it is a mixture of experts (MoE) model like the 2.x models, won't this reduce the hardware needed to run the model?
The Kimi-K2.6 model is 1.1T parameters with 32B active parameters. With light quantization (Q6_K) that's enough to run it (slowly) on a single 5090. On a single B200 you can have 5-6 experts loaded into VRAM at a time. Realistically that would be 3-4 to account for the context. [!]
[!] With this and other MoE models it looks like an interesting area for research would be to detect or predict which models would be needed ahead of time. That way you could schedule the load into VRAM step before the weights are needed. That way you shouldn't lose much/any performance from offloading the weights to RAM.
You need whole weights in VRAM for optimal performance. Don't be confused by "experts" in the name -- you don't get to load static subset of experts and blast next 100 tokens with them. In typical MoE model they get switched "randomly" on every token, so all experts have to be readily available.
> With light quantization (Q6_K) that's enough to run it (slowly) on a single 5090. Kimi K2.6 is released as INT4 already.
So 5090 with K2.6 is just gonna sit idle 99% of the time, waiting for next slice of weights to load.
5.6 Sol calculates that single 5090 in raw compute & memory bandwidth can run K2.6 at 35 t/s (256k context depth) -- if it somehow had enough memory to hold whole model in VRAM. Man, I hope HBF succeeds and Nvidia brings it to consumer cards in 5 years..
2 replies →
> The Kimi-K2.6 model is 1.1T parameters with 32B active parameters. With light quantization (Q6_K) that's enough to run it (slowly) on a single 5090
Without leveraging system RAM and/or SSDs, I don't think you can, or how exactly are you running this, if this is something you are doing today? With CPU/expert offloading you could probably do it with a 5090 + 1TB of RAM or something like that, but absolutely not on a single 5090 entirely within VRAM.
4 replies →
I assume you mean putting only the 32B active parameters on the GPU, and the rest on a bunch of regular server DRAM like on a 768GB to 1024GB RAM server?
Because Kimi K2.6 in Q4 is about 584GB GGUF size on disk and will use slightly more than that in RAM, Q8 is 595GB.
https://huggingface.co/unsloth/Kimi-K2.6-GGUF
You're talking about running this "at home" for 1 user, using a mix of VRAM and RAM (total should be ~1.5TB). That's certainly possible. It'll be slow, especially prompt processing, but doable for single users.
But my comment on running it was more towards serving this profitably at scale. You get much better throughput / unit of compute if you load everything in VRAM and serve many requests at the same time. That's how all inference providers are doing it.
1 reply →
If it takes so much resource to run, how does the sharing of a single llm works? There is some interface that basically submits context/cache plus current promt, from each user, doing basically time-sharing compute?
I believe they batch requests so the same weights in vram are shared across many requests https://www.baseten.co/blog/continuous-vs-dynamic-batching-f...
We have a lossless compression codec (working on open sourcing it over the next couple of weeks) that reduces it down to its minimum entropy -- it cannot be compressed further. On all tested large models, it's a ratio of 1.34-1.23 -- and smaller models up to 3.76x. It also increases the effective bandwidth by the same rate.
Exploring compression algorithms for weights is a good idea, and I hope you have a successful product. However, if you can prove this statement:
> reduces it down to its minimum entropy -- it cannot be compressed further.
I think you could make a lot more money elsewhere :-)
https://en.wikipedia.org/wiki/Kolmogorov_complexity#Formal_p...
1 reply →
That's very interesting. Does that mean you can reduce say, a 30B class Q8 from ~30 GB down to 10 GB or less?
2 replies →
We have a lossless compression codec (working on open sourcing it over the next couple of weeks) that reduces it down to its minimum entropy
LOL
[flagged]
1 reply →
This is a very insightful eye opening take. I haven't even thought of it this way. This really is the first open model to be as big as the frontier has been until now.
I think this release is actually great both ways when you think about it. We gonna be able to learn knowledge that labs have been hiding from us (e.g. cost like you mentioned). And labs could learn from whatever optimization techniques people come up with when trying to host this model.
It's honestly just good for everyone in my opinion.
>realistically you'll need 16x for context / throughput optimisation
Sounds like I'm buying a lottery ticket this week so I can drop $800k on hardware.
I think cursor will likely do a grok fine tune rather than a kimi one for the next composer.
they noted in their blog post they didn't focus purely on coding for grok 4.5.
Most likely, since they were acquired. But for us outsiders it would be a cool thing, to see if the delta is the same between kimi2.x + cursor data -> kimi3 + cursor data.
So nowadays the hardware and hosting providers must be in an optimization race, whoever can make the model just a bit smaller or more efficient (to fit on fewer/less powerful cards) will have a huge advantage and can make a lot of money.
I am curios what's the most profitable thing to "plant" (agriculture analogy) on the land (cards) that you have have: web hosting, vps, llms, image/video generation, etc
> The latest AISI benchmarks on cybersec place it above glm5.2, but still way way behind SotA closed models.
Sota closed models don't even answer cybersecurity questions lol.
> if "labs are subsidising tokens on API pricing"
> SemiAnalysis estimates that Anthropic's current blended gross margin has risen to the mid-60% range, with the API business gross margin exceeding 80%
Of course, people will insist "they are lying", "why should we believe them, it's well known they subsidize API pricing", ...
https://newsletter.semianalysis.com/p/anthropic-3q26-profit-...
https://finance.biggo.com/news/02d45650-b569-4d12-b44d-8d6d8...
Agreed. My (somewhat educated) guess is that top labs have healthy margins on API pricing. But this release will add another 3rd party / clear of conflict datapoint in this estimation.
even deepseek, with their current (dirt cheap) price, can earn enough profit to cover the cost (hardware investment?) in 10 months.
2 replies →
That numner blends in training or no?
pardon my ignorance but is fine tuning still considered viable in face of rapid model releases. Is it really worth it?
my friends whove tried in their companies gave up on it.
Anyone who thinks that the labs are not profitable on per token API pricing is delusional and hilariously wrong.
It all depends if you count the fixed cost of training or not. And the cost of the hardware.
2 replies →
[flagged]
It is online on https://app.fireworks.ai/models/fireworks/kimi-k3 (Uncached Input $3.00/M Cached Input $0.30/M Output $15.00/M)
Fireworks' priority tier of Kimi (at $3.75/M vs. Moonshot's $3.00/M) is available on OpenRouter as well. https://openrouter.ai/moonshotai/kimi-k3#providers
Currently it's showing significantly better latency, but at a fraction of the usage Moonshot is experiencing, so we'll see how that holds up - regardless, a same-day deployment is an impressive feat!
I've used GLM-5.2 a lot on fireworks and had never ever issues on rate limits. If they cannot handle the load with K3, there's the priority tier to get your evals done.
I'm definitely having full eval suite on already if they get overloaded later on.
Comparing to Opus 5: Claude Opus 5 (Uncached Input $5/M Cached Input $0.50/M Output $25/M) but you also pay a premium on Cache write 25% for 5m and 100% for 1h.
Then there’s the questions of token efficiency and token quality.
from the license:
If the Licensee or any of its affiliates operates a Model as a Service business, and the aggregate revenue of the Licensee and its affiliates exceeds 20 million US dollars (or the equivalent in other currencies) in total over any consecutive 12 months, the Licensee must enter into a separate agreement with Moonshot AI before using the Software or its derivative works for any commercial purpose.
good find! This sounds a bit like what Meta was doing with the earlier Llama models?
There is also this paragraph in their licence that is smart marketing-wise:
> 3. If the Software (or any derivative works thereof) is used for any of the Licensee's commercial products or services that have more than 100 million monthly active users, or more than 20 million US dollars (or equivalent in other currencies) in monthly revenue, "Kimi K3" must be prominently displayed on the user interface of such product or service.
Meta had much higher limits and not restricted merely to token resellers
Is that even enforceable?
1 reply →
I feel like most hardware to run LLMs on is shaped wrong for individuals.
It's either having a model struggling along with like 5-10 tokens per second on unified memory, or data center cards with hundreds of GB of VRAM consuming more than a kW of power. It doesn't seem like there's prosumer GPUs with like 180W-250W TDP and 128 GB or 256 GB of VRAM (one can dream). Then bifurcation and even just two of those cards would be kinda useful (albeit NVLink or equivalent would need to be commonplace).
Obviously nobody is running Kimi K3 locally without an insanely beefy homelab and lots of money to burn, but running GLM 5.2 would be cool at like ~100 tokens per second for a single session and maybe ~60 tokens per second with N subagents.
How unfortunate.
I have found that the "mostly didn't lose anything" Q8 large models that I want to run are all too large to run on the "only $3995!" 128GB max RAM systems that some people are buying, and definitely won't fit with any usable amount of context. Things like Qwen 3.5 122B Q8 or deepseek v4 flash Q8, or Laguna S 2.1 Q8 need 170-190GB of RAM including full context, which fits on a 256GB RAM dual socket workstation or rackmount server (sans GPU).
Copy and paste below from my notes and reported memory consumption with latest llama-server, assuming use of "--no-mmap" to load the entire thing into RAM at the time that llama-server launches.
DeepSeek-V4-Flash-UD-Q4_K_XL via unsloth 145GB on disk GGUF 0.03.323.204 I common_params_fit_impl: projected to use 178175 MiB of host memory
DeepSeek-V4-Flash-UD-Q8_K_XL via unsloth 151GB on disk GGUF 0.02.215.885 I common_params_fit_impl: projected to use 184636 MiB of host memory
Laguna-S-2.1-UD-Q8_K_X via unsloth 120GB on disk 0.01.616.119 I common_params_fit_impl: projected to use 172860 MiB of host memory
Qwen3.5-122B-A10B-UD-Q8_K_XL via unsloth 160GB on disk GGUF 165GB RAM use on launch, fresh context 0.04.976.905 I common_params_fit_impl: projected to use 170038 MiB of host memory
DeepSeek-V4 should use only 5GB for context due to CSA and HCA, see figure here: https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro
But not every framework implements it properly yet.
1 reply →
There's an emerging practice of using Q4 quants and Q8 KV cache for local inference. At that point you can run both Qwen3.5-122B-A10B (my personal choice on Framework Desktop 128gb) and Laguna-S-2.1.
Now whether that's good enough for one's use-case remains to be determined. You can also get more out of those (local models and quantizations) if you further tweak the harness you use them with, but tbh this is where it gets too much work (at least for me and the time I have available).
7 replies →
Post-crypto, the GPU manufacturers took the proactive move to use VRAM to segment the market for the purpose of price discrimination. Sure, data centers will pay vastly more for GPUs, but Nvidia knows that the PC market is steady and reliable. They could get the best of both worlds by kneecapping their consumer cards to tiny amounts of RAM, to dissuade the cloud providers from scooping up all the consumer cards, and then charging the two segments wildly different amounts for what amounts to the same hardware (back when the cost of RAM was negligible)
LLM inference unfortunately also seems to be a task that's poorly formed for moderate consumer hardware,as a single user. For a single user use case, the load is bursty but requires the weights to be in memory already. So a multi user server that keeps the model weights in parts of its memory and then spends some more per user kv cache is wildly more efficient and the wildly expensive gpu cores aren't just sitting idle most of the time. Don't get me wrong, most desktop workloads are bursty, but the power needed to to them has gotten cheap enough that we can have way overkill for idle scenarios hardware just sitting on our desks.
Why does it have to be so bursty though? Just let it run multiple continuous-batched inferences overnight. This would work especially well in combination with SSD offload, and given any kind of sparse attention (common in more recent models) even swapping out the KV cache itself to disk might ultimately be a win. I wouldn't be surprised if something like that ultimately became feasible for single users running even K3 itself.
6 replies →
I've been feeling for a while that as we keep increasing model size, we're going through the opposite of the PC revolution.
The "democratisation" talk from the frontier labs is especially egregious when they only release closed models (gpt-oss hardly counts) and are trying everything they can to make it harder to run open models.
Yeah, I've been experimenting with DiffusionGemma which sadly isn't as smart as Gemma itself, but holy hell is it FAST, and has image input as well, so doing things like "take a screenshot once per second + ask the model to categorize/model it WITH reasoning before" becomes realistic and doable.
I ended up implementing DiffusionGemma myself with Candle in Rust + CUDA, and it's quite literally the fastest model I've managed to run on my hardware.
I agree but worth noting that it's never gonna be very practical to run LLMs like this at home. Unless we have some sort of design breakthrough, the only "sensible" way to run them is at high batch levels on shared HW.
Like, yeah if I could spend a few grand on such a GPU I probably would coz I'm a rich nerd, but I'd acknowledge it as an extremely inefficient luxury, kinda like a sports car.
So I think you could say the real misfortune is that we don't really have the technology (be it computer tech or political/social tech) to do that shared-HW thing in way we can truly trust.
We could make LLM inference 100x cheaper to run at home efficiently, but that solution might need to be updated every 1-2 years, whereas current GPU are useful for various others tasks and last longer
"Never" is a long time. Just think about how much ram we had 10 or 20 years ago. 1.5TB isn't a lot really.
1 reply →
‘Never’ is a big word in the computing world. 10 years from now a model this size will probably run on a high-end phone.
Of course, by then we’ll want to run something commensurately larger.
The next mac Ultra will allow to run a big model locally with acceptable speed. But we need people to optimize it for that computer, and we’ll be more limited in models we can choose from
128GB is enough to run a large model, quantized, REAPed, with MoE and fast SSD for model weights
Not Kimi K3 large though
2 replies →
> like 180W-250W TDP > running GLM 5.2 would be cool at like ~100 tokens per second for a single session
Your power consumption estimates are off for this generation of GPUs. A 27B dense model gets 50-80 tps on an RTX 6000 using 600 watts.
An AMD R9700 gets 20-50 TPS at ~300 watts on 27B. 100 TPS for the 35B MOE model. And there might be some more optimizations to that as AMD software support gets better with ROCm's latest versions.
1 reply →
RTX Spark does go up to 128gb No idea how it compares tho
I have one. The limitation (beyond total size of the memory) with the Spark is DDR5. "Real" inference hardware is HBM (high bandwidth memory) which is like 10x the performance.
So for prefill -- which is more about compute than bandwidth -- the Spark performs quite admirably. But on decode it's highly bandwidth constrained. Some smaller MoE models (e.g. Gemma4) can do 60-70 tok/second but anything dense, or anything that is actually filling up most of that 128GB is going to choke out around 15 tok/sec. Even at NVFP4.
My experiments with this are at https://github.com/rdaum/eider/
For my current work I get to log into trays on a real GB300. It's somewhat comical that NVIDIA is marketing the little baby on my shelf here as even in the same universe as that. Which is basically like having access to a super computer.
You're right, and it's interesting to consider why. It's probably a combination of a few factors:
1) Local LLMs are a relatively new phenomenon and hardware takes years. Apple probably lucked into their unified memory architecture being suitable (in terms of memory size and bandwidth) for local LLMs, but it's only with the newest generations we're hearing about LLMs even being a consideration in their design process.
2) NVidia seem to be deliberately blocking consumers from taking this path - as evidenced by the removal of NVLink from the 30x0 series onwards - probably to protect their data center cards from internal competition?
3) Perhaps there's just not the market for it? It's feasible that the number of nerds interested local LLMs is very small in numbers, sales, and profit potential compared to gamers on the one side, and data centers on the other. (This would explain why AMD and Intel aren't trying to out-innovate NVidia in this area, despite it being an obvious opportunity.)
There will be a huge market for local inference once it's cheap and widely available.
Try to imagine output token speeds of 15,000 tok/s and a time-to-first-token of 200ms. (This has already been done for Llama 8B.)
Now imagine gargantuan context windows (2M, 4M, or even bigger); keep in mind the 1M context windows were science fiction a few years ago... now imagine having this on a local model on something like a phone or portable device that can be gathering data about things you're doing and constantly run inference for things useful to you. An obvious example of this would be a chatbot you can talk to that responds like a normal human conversation and doesn't have delays, but that's just scratching the surface.
1 reply →
The individual-shaped-hardware problem gets even sharper at the phone end. Shipping a 3B model on-device, the usable RAM budget after the OS and everything else is more like 2-4GBtotal, not per-model so it's not 'can I afford more VRAM', it's 'can I fit a language model and an STT model and embeddings without the OS killing my process'. Feels like phones are the most hardware-constrained 'individual' tier and get the least airtime in these kind of discussion. Is that because the models that fit are still too limited to be interesting, or something else?
Recently spent a few hours messing with bonsai 27B and ternary bonsai 27B at total weights + context fitting in slightly under 6GB RAM, and it's just dumb as hell. It writes what seems like grammatically correct content but it's extremely limited.
It will also happily hallucinate new names and content to fill in gaps in its knowledge, and present the hallucations in what looks like a correctly formatted sentence, so it could fool a person who doesn't know the subject matter. Like, I asked it for a description of Seattle and it hallucinated a name and description of a nonexistant tallest building in the city and suggested the view from its observation deck .
https://prismml.com/news/bonsai-27b
https://huggingface.co/prism-ml/Ternary-Bonsai-27B-gguf
In no way was I surprised, it's asking a lot of under 6GB RAM usage. But I think for 99% of people they will get better results doing something over the network where the weights and inference engine are not on the device.
1 reply →
We already know that competition brought GLM 5.2 prices down roughly 45% since its release on June 16th (1.5 months ago), and the price downward slope is probably still going (I've been checking regularly and new providers keep fighting on price, I don't think prices have settled yet). For reference : https://openrouter.ai/z-ai/glm-5.2#providers
I saw arguments like "Providers cannot price less than their costs" in other comments. In economics, it's generally admitted that they shouldn't price less than their marginal costs, i.e. in their case roughly the cost of electricity, since a lot of these datacenters are not at capacity in terms of graphics cards usage (speculation since it's very easy to rent a GC for a couple hours on some providers). My guess is that someone will be selling tokens at less than electricity + depreciation of GCs soon, since there's a lot of competition and "smaller" data centers have overcapacity? This is speculation, correct me if I'm wrong
Seminanlysis is estimating sub $1 cost per MT for ~2Trillion models. The numbers change based on throughput and quant, but it is conceivable that provider costs at scale are low enough that even $2.42 per MT on GLM 5.2 (current best price) is margin positive by a wide margin.
> My guess is that someone will be selling tokens at less than electricity + depreciation of GCs soon, since there's a lot of competition and "smaller" data centers have overcapacity? This is speculation, correct me if I'm wrong
My guess is they are selling you the tokens, then selling your tokens (data) onto someone else.
I see these conspiratorial arguments all the time and I think people massively overestimate the value of the average users tokens.
The problems with frontier models (design taste, ability to solve novel/difficult problems, etc) cannot be solved by throwing more slop from the average user at it.
Actually, most of the main deficiencies in current models stem from the fact that their data sets aren’t curated and specialized enough.
3 replies →
Press x to doubt on the 45% number. The cheaper providers on open router are fp4 vs fp8 for official zai. There are some cheap fp8 ones (like novita) but the ui makes it seem like it's a temporary promotion, with their normal prices being almost equal to official zai (idk much about open router so not really sure what's going on with these discounts)
Yes it's true that it's not super clear whether these prices are permanent or short term promotions. On the other hand, there are so many providers making promotional offerings that you could probably easily switch from one to another should their prices go up?
If you click the provider it shows the precision, 45% off at AkashML shows FP8. The drawback is the small context window, at 96k.
Then there's 43% off at StreamLake with FP8 precision and 1M context window.
There is nothing to doubt, the cheapest price on openrouter is ~45% lower than when GLM5.2 was released.
[dead]
Getting 404 on the OP's link. Does it mean it got banned or self-censored in the meantime?
Until a few minutes ago there was a countdown page. (The weights haven't been released yet.) The countdown should be over in 19min, not sure why we're suddenly getting a 404.
Maybe they are in the process of uploading the weights and git history and have taken down the holding page/project to not have the "coming soon" in the git history.
It's up now
I imagine it's just technical issues on the flip. It's also going to be interesting what happens to HF with loads of people downloading a many TB model. Even though almost no one has the capability to run it, it does seem like something to stash away in case it suddenly becomes unavailable due to government controls.
FWIW, China is suddenly talking about model export controls. It was one thing to release also-ran models, but now that they're pushing SOTA it's a different game.
> FWIW, China is suddenly talking about model export controls. ...
Thanks for the hint. It makes sense, even if the main driver for releasing the models is to reduce the market size for the US companies.
Do you have any sources?
Edit: "market size"
1 reply →
Honestly it's pretty wild that the standard way to download these isn't torrent instead of Hugging Face direct. Why doesn't HF themselves provide torrent links?
At the risk of sounding like a conspiracy theorist, this sounds like a great opportunity to make a statement. US or China, but likelier to be the former. Maybe Clem's on a call with the US government right now?
The wonderful imagination of the outsider
Who is Clem?
Open source teams have had access to the weights for at least a week now. vLLM folks expect full support on public release of the weights. Anything conspiratorial won't prevent the weights from leaking...
It's just launch day gremlins, like always.
In my opinion, next step is to cut down on reasoning tokens while maintaining intelligence. The Chain of Thought and looping can still be an issue with these Chinese models. They in fact said K3 would improve in the area but it's still an issue that unfortunately harms the token cost wins a bit. OpenAI has been really impressive here, on the opposite end of this.
There is a really interesting startup in Prague that is doing just that. They fine-tuned Qwen 3.6 27b to have 46% fewer reasoning tokens while maintaining most of the performance characteristics. I'm interested to see if they continue down this path of optimizing reasoning for other models.
https://bottlecapai.com/post/thinkingcap-qwen3-6-27b/
Yeah, they thing forever and doubt everything "wait but" for 200k tokens for almost any question.
On the flip side, I really like being able to inspect its reasoning chain thoroughly, as opposed to the "black box" that Anthropic models are now.
6 replies →
Looks like it's live now, it's approx 17GB per safetensors file x 96 files, so so about 1.63TB. I can only imagine that people with their favorite quantizing tools warmed up and ready to go are aggressively downloading it now.
There's a 2bit quant on HF already at ~1TB
Given the frontier-level capabilities of Kimi K3, I'm wondering if it's possible to extract the core capabilities (fundamental reasoning and tool calling) of the model into a smaller one that consumer devices could run? Not sure exactly how, but either by heavy distillation or some other surgical method since Kimi has a Mixture of Experts architecture.
I think it's very valuable to have a smaller model that doesn't have any domain knowledge or facts built into its weights, but given the right context, could accurately reason about what to do and use the right tools.
I'm aware of colibri [1], but so far I've only seen extremely slow performance.
[1] https://github.com/JustVugg/colibri
"I'd like a car that goes 300mph and gets 100mpg while doing it. I'm aware of a car that gets 100mpg but it is extremely slow."
You are describing fundamental tradeoffs. Getting more performance relative to model size and training token amount is what all of the labs are solving.
Labs are focusing on creating models, small or large, that perform well on various benchmarks, including general knowledge, domain-specific expertise, and agentic capabilities.
Asking for such a model while wanting to be small and fast would align with what you're describing, which I believe is different from what I'm pointing to.
The model I'm describing sacrifices domain knowledge and expertise for agentic reasoning and tool-calling capabilities at a reasonable speed.
Think of Cactus Compute's Needle [1].
[1] https://cactuscompute.com/blog/needle
1 reply →
Why not generate an artificial dataset using commercial APIs and then finetune a small model on this data?
I’ve had success adapting even a 7B model for single-domain tasks that way, including reasoning and tool calling.
You can use an open model. The point is just to outsource the inference, so you don’t have to deal with running the larger model yourself.
This is probably one of the ways to achieve this. I see a plethora of such fine-tunes on HuggingFace [1], but they're either not much different than the base model or they're outright benchmaxxing.
[1] https://huggingface.co/models
There’s another way besides distillation that’s way cheaper: You can have the big model build prescriptive skills that the small model follows.
Take the “train” portion of tasks on some benchmark, have K3 complete it, and then output detailed descriptions of tools used and why, then run the validation tasks with some small model that has access to the skills.
Yes. Using a harness with a strong model to create lots of utilities and tools for yourself is effectively the same thing.
Isn’t that distillation ?
1 reply →
I wondering if folks like OpenAI & Anthropic start supporting open models in their api. After some time, keeping users stuck is going to be more important than "models"
What grip do they have then ? Is Claude code and the suite of other interface that good compared to open source/ competitor offering ?
K3 releasing as open source right at the same time that people are criticizing Opus for questionable performance (there's even a thread on HN about Opus 5's problems)... this is such a flex.
> (there's even a thread on HN about Opus 5's problems
is opus 5 a flop like 4.8 ?
where is the thread btw curios
There's two threads now, apparently
https://news.ycombinator.com/item?id=49068029
This is historic. For the first time, an open-weights LLM is right at the top.
We won't be able to run this ourselves, but many providers can.
> For the first time, an open-weights LLM is right at the top.
Hmm, not quite true, I think that honor, for better or worse, goes to OpenAI. When they released GPT2 (or GPT1 for that matter) is was quite literally the SOTA in the ecosystem when it was released.
When OpenAI was actually still a proponent of open AI...
You are correct. I miss the time when OpenAI was open.
thank you embedding-shape
[dead]
Did someone run censorship and political bias tests on this ? Must be interesting.
As a completely one person, single sample anecdote, the 'heretic' uncensored Q8 GGUF variants several people have published of Qwen 3.5-122, 3.6-27B and 3.6-35B-A3B will very happily discuss just about any controversial topic that the CCP hates. Including lots of things that would get you thrown into prison if you published them in Mandarin on the domestic Chinese internet.
https://github.com/p-e-w/heretic
As a side note on this, if you see the reference in the screenshot in the link above to the harmful behaviors prompt set, these are all in English:
https://huggingface.co/datasets/mlabonne/harmful_behaviors
You could likely further de-censor a model by having a set of 'test' prompts in native Mandarin, Cantonese or really just about any other language. I don't speak any Chinese languages so I don't know if the published 'heretic' GGUF files some people have been throwing around will cooperate, or refuse, if you ask it in Mandarin for how to build a meth lab or precursors for semtex.
That's a lot of words to say "No, no have has seemingly done that yet with K3".
5 replies →
Outside of asking it to talk about Tiananmen Square, are there any standard tests for "bias"? And if so, who created them and what are their biases?
Is Taiwan a country? What does it mean to have an efficient market?
It is more important to focus on the questions than the persons who created it.
It would, indeed, be interesting to compare, given what we know about Anthropic’s censorship and political bias in their closed and more expensive models.
https://x.com/dhh/status/2081435006770249831 (from the creator of Ruby on Rails).
In his specific case Kimi did the task it was asked to do (translation of the article DHH wrote), which Claude refused to.
we need open models because they let me dehumanize roma ppl. great take by dhh.
'When gypsies appropriate public spaces, you deport them. It's not hard, it's not cruel. It's the basic logic of self-protection.'
1 reply →
There's is always one in each and every AI forum: "But, but have you asked it about tiananmen"?
[dead]
I heard this is the talk in town these days. Why can't Meta keep up? With >10000000x more resources you'd think that they'd be able to introduce equally performant if not better open weight models
The SemiAnalysis piece on this is long but very much worth reading:
> The company appears burdened by far too many disparate groups that are over-optimizing for certain metrics as opposed to delivering usable technology for the company as a whole.
> And because Meta has a reputation for throwing money at problems and executing at high speed, these U-turns end up becoming more costly versus other companies that take a more disciplined or conservative approach. Suppliers also lose faith when given design wins are later cancelled. This has lead to less supply chain prioritization on new designs. Some suppliers favor focusing on Amazon or Google designs due to Meta’s frequent reshuffling.
> Few inside Meta’s chip division have a full understanding of why the company bought Rivos in the first place, and those who championed the deal internally have since gone quiet.
etc etc
It goes into a lot of depth.
https://newsletter.semianalysis.com/p/metas-infrastructure-t...
he seems to be bullish on meta though and considers muse on slope than an intercept
https://newsletter.semianalysis.com/p/the-future-of-meta-sup...
The cynic in me says maybe they would be further along if they hadn't spent $80 billion on trying to build the "Metaverse" VR world. I've never met anyone who actually uses it and to the best of my knowledge it has very low mass market uptake.
https://finance.yahoo.com/sectors/technology/articles/mark-z...
Not exactly the best use of dollars and the labor hours of some of the best minds of our generation.
Particularly when you could vibe-code Metaverse VR for a lot less than $80bn.
Because lack of talent and organizational disfunction matters a lot more than you think. The reason why OAI and Ant are always at the top is because of this and I’d say compute is third on the list.
I would argue that they actually don’t lack talent, they have an insane bench of really smart people. What they lack is any sort of direction and leadership. They are a ship lost in the ocean and up until now have been lucky to find a few treasures along the their way.
2 replies →
because imagine starting work every week and finding that your dumb ass CEO pivoted the company again and is ruining other peoples lives, and he then reorgs the management again so you now have your 5th leader this year.
Morale and momentum are huge things in companies, Zuck has been murdering both of those in Meta since... well naming it Meta.
Turns out sitting quietly in a room and doing math is worth more than all the money and network in the world.
At this point in time what does meta get from releasing open weight models? Why devote the resources to it.
Why would there be any motivated person left in this place.
You can make the same argument for closed models. Why spend hundreds of billions training larger and larger models when you can just use Chinese models? Spend that money somewhere else further up the stack where there’s more value. Let China do the training since they’re so efficient at it.
4 replies →
Is there any (near future) technology that would permit burning this terrabyte into some kind of ROM chip?
The path to ubiquitous AI (17k tokens/sec) https://chatjimmy.ai/, but it's running the rather outdated Llama 3.1 8B
Yes, from 6 days ago: https://news.ycombinator.com/item?id=48986351
That looks promising! As models become a commodity, this may turn out to be the real AI gold rush.
A question of course would be "is 15,000 tok/s Gemini better than 100 tok/s Opus 5"?
2 replies →
Given how fast models are improving, burning the weights into actual ROM is prohibitively expensive if you need (or want) to replace the chip every couple of months.
The alternative is on-TPU flash for storing the weights.
Yes. We're still a ways off from this being ubiquitous, but I am convinced it's coming.
So, in normal parlance this is a 2.08T-A104B model at MXFP4 (weight) * MXFP8 (activations)
Perhaps let's call it Kimi-K3-2.08T-A104B to make matters clear.
Its now on Nebius: https://tokenfactory.nebius.com/?modals=endpoint-details&mod...
$3.00 / 1M In; $15.00 / 1M Out; 120 Tok/s
But since for reasons only Nebius knows Token Factory in general does not seam to offer prompt caching (at least not discounted) its essentially useless.
From a cursory glance on huggingface, the files don't add up to 2+TB. Unless it adds up to that when you extract the multiple ~17GB files, if that's the case then that's some crazy compression.
If it's 4-bit native for the sparse parameters (which is the bulk of them) why would you expect it to add up to 2+TB?
Kimi K3's full weight is now live on Hugging Face https://huggingface.co/moonshotai/Kimi-K3
Did the link change or anything?
Getting 404 Sorry, we can't find the page you are looking for.
It's up.
the page is now throwing a 404 11 minutes out.
Can't wait to run this at 0.02 tokens/sec on my CPU so I can get a response just in time for next month.
Unfortunately I don't think modern consumer CPUs are physically capable of addressing enough RAM to even load the model into memory. We'd have to wait for some random person to make an extremely quantized version before we could reach those blazing speeds
Less than 2 hours left to the Kimi moment. It’s been more than 2 years since the DeepSeek moment that shook the world.
Coreweaves gonna boom
This has to be one of the craziest uploads on the internet up until now.
Raw fucking intelligence at your disposal, free to download.
If you'd describe what's happening now to someone from five years ago they'd think you're hallucinating or mad.
I think we felt the same when Apache or MySql was releasing back in ancient times.
Apache and Mysql aren't general purpose brains
That would be 7/27.
China uses YYYY/MM/DD, which is logical.
What China (and Japan) uses is YYYY年MM月DD日, which IMO is the superior date format since it's self-explanatory - the sections are spelled out right there!
the only logical format.
signed: a hungarian :)
8 replies →
20270727 if we're improving dates :)
Jumbling together year, month and day and having to separate them by counting digits is not an improvement for human readability. (And you have the year wrong.) Any of “27 July 2026”, “July 27, 2026” or “2026-07-27” would be superior.
1 reply →
ISO 8601 ftw
270727 if we want to save tokens :)
1 reply →
Looks like another LeetCode problem about checking for anagrams.
or 27/7 for the rest of the world
Most life forms don’t use any calendar actually.
1 reply →
No, 27-7 for the rest of the world.
The separator is often the only way to distinguish American notation from ISO, so please use a dash for dd-mm-yy and a forward slash for mm/dd/yy
9 replies →
Or 11/Shrawan 2083 if you're in Nepal
They release it before I could even get a kimi subscription because of waitlist? lol hard to believe that I might get a kimi subscription from a third party
I just checked and I have it available in opencode go! I just tested it with one message and confirm it works.
It's not practical to use it though. It counts almost 8x more towards your quota than glm 5.2!
https://opencode.ai/docs/go/#usage-limits
I wonder how long it will take for this to get fully decensored and for bad, BAD things to happen
[flagged]
I would like to live in a world where saying a slur is the worst thing I can imagine a computer doing
404 is resolved let the downloads begin
American dates are sooo fucking annoying…
is there a realistic way to distill 2 consumer hardware friendly models with max ~200B and ~20B? Qwen did it, but would it be possible for 3rd parties (unsloth etc)?
Yeah, why not. Toughest part is running the hardware so you can create the traces for downstream training, but once over that hump, nothing would stop you from doing that no.
Are they going to release Kimi K3.1? I’m eager to test it. According to rumors on X, it could outperform Fable. Could it be the first Chinese open-weight model to become the leading frontier model?
Hoping no issues on Huggingface due to download rush.
For huge models like these, the only reasonable way to host them is via torrents. I don't understand why hf doesn't offer this as an option.
Linux distributions got this right: Offer both HTTP and Torrents. Let the user decide.
I believe they don't do torrents because it gives them a lot more control.
Like they can takedown or update downloads and they can prevent someone from trivially bypassing the license agreements you need to accept for some models.
> Let the user decide.
Perhaps that's exactly what they're trying to avoid, giving the user any form of control and having them depend on HF.
I've had a steady 2 gigabits (my maxxed out ISP bandwidth) since I started the download at launch.
It’s going to get very little downloads just by virtue of size. Very few shops will be able to directly use it
it's a 404 link now
This looks really promising. Excited to see where this goes. Looking forward to trying it out!
Wait, so I can download it and run it locally now?? Wow... But it probably won't work on my computer, right?
The short answer is no, it won't work on your home computer. In it's current form it needs something like 594 GB of memory, far outside what you can reasonably run on normal consumer hardware in 2026.
If you have really high end hardware, you might be able to squeeze a heavily quantized version of Kimi-K3 onto your rig, but it will be too slow or too lobotomized to be useful.
This does put a near state-of-the-art open weights model within reach of what a small or medium business could afford if there's a case for local inference. It's probably not as good as Claude Fable or ChatGPT Sol. But if you're an organization that has a genuine need to run inference locally, this is a real possibility.
Is this for your homelab? Not in any practical sense.
Is this a possibility for organizations that can justify $1M or so on hardware for a near SOTA model they have full control over? Yeah, absolutely.
The full K3 model will probably be way more than 594GB, that's more of a plausible range for Kimi 2.x. You'll probably be able to test run this model at full or near-full precision using SSD offload, but only at very slow speeds - probably slow enough that you'll be forced to let inferences run overnight or even spanning multiple days. Mind you, that's still useful enough for many casual users, given that they're running a near-SOTA model!
[dead]
Yes it will. Buy a 4TB nvme, allocate 3TB as swap, and run a gpu emulator on your cpu.
I can't imagine a GPU emulator would run better than straight CPU.
Right
Why is there a countdown?
You're not having a party?
I think it's shameful that Moonshot isn't providing us with party kits like Microsoft did with the Windows 7 Launch Party kit. How am I supposed to properly celebrate this without fun Kimi-themed quizzes for my guests?
1 reply →
It saves you from having to perform date-time calculations.
It's a release party
Seeing 404
Good enough is often the right call
I don’t need the fastest car to get to where I’m going. I need a car that gets me to where I’m going at the speed I’m comfortable driving at.
The weightings should be released on July 27.
how feasible its will be to run on modal or deepinfra? anyone here tried and tested such large models running?
Modal eng here. Getting the model running is quite challenging, but its accessible right now on Modal via Endpoints: https://modal.com/blog/kimi-k3-by-moonshot-now-available-on-...
15/million. that will be much higher than subscribing claude or open AI right
maybe a quantized version on a GB300 would work? unsloth hopefully working on it.
The VRAM, power, networking, and operational requirements put it beyond the reach of many enterprises.
There's no going back on this. This is putting a very capable intelligence in the hands of the masses. Private companies in the US are aching for Trump's protectionism but it'll do nothing. The hardware needed to run this is ofc prohibitive, but actually putting it out there feels like a 'RSA source code on t-shirt' moment for humanity.
No, luckily private companies in the US are aching for this to NOT be banned. NVIDIA, Microsoft, etc. just released that letter. We’re saved from the trillionaire companies (OpenAI, Anthropic) by the other trillionaire companies acting in self-interest (hosting and hardware).
I don't know if the masses can quite afford the 500k in GPUs you need to run this
a "moment for humanity"? as if this shit isn't going to generate 99% slop at the cost of all we have left as a species?
Sometimes I’m not sure who is more unhinged: the total AI kool aid drinkers who think this will make us all into immortal demigods (or take over the world as it goes “foom”), or the AI doomers and haters who exaggerate everything potentially negative about it and react to it the way a 1980s Christian fundamentalist reacted to rock music.
It’s a new fundamental innovation in math and CS that allows large scale lossy compression of natural language another data formats in a way that is semantically queryable and cross-referenceable. It also manifests some form of emergent intelligence, likely evidence of the long posited link between intelligence and data compression.
The tech is awesome. It’s one of the coolest things I’ve seen in over a decade. The industry is kind of shitty, which is not unusual. The discourse around it is almost universally insane, crazy people arguing with crazy people.
Oh and get off the AI eco bullshit train. Look up the energy cost of AI queries vs driving or running a home air conditioning system. Feel bad about using AI? Skip that DoorDash order. You probably just saved the energy of 1-2 days of heavy Claude Code use.
There’s going to be a lot of competition around this model. Let’s see how low AI providers are willing to push prices.
I think the results might be underwhelming - AI providers need to turn a profit and can't subsidize, and they're working off of the commodity hardware everyone does.
I wouldn't be surprised if they started offering potentiall bad quantizations with much reduced capability at lower prices (without telling the users, of course)
I would be surprised, considering that OpenRouter requires disclosing the quantization and shows automatic benchmarks to compare between providers for the same model.
2 replies →
As long as they are transparent about what quant they serve the model and any other optimization they do that also affects performance of inferred tokens.
...does Hugging Face have enough bandwidth to let people download en masse however much file size a 2 trillion parameters model is?
I have a feeling the number of people downloading 2t parameter models is significantly smaller than the 1-100b models.
So... Now we give huggingface the hug of death - right? ;)
It's thankful that openAI or anthropic haven't IPOed yet. Or terrible for some
Strange communists, giving away such an expensive model to the public.
On the other note, can't wait to see 1bit quantisation soon and how it performs in benchmarks, if it performs really well in benchmarks, would be very good news for GPU hosting providers, to offer "Opus 4.5 level model at the cost of Haiku 4.5"
I think China publishing this stuff is more about prestige. The US has had export controls that make it illegal to sell Nvidia chips, and other AI hardware to China, and this is China saying "yeah, whatever". Also, it weakens western tech companies' position in AI, and pushes CCP bias perniciously. Building your product/company on top of a text-generation model that favours the CCP position on everything is just peak propaganda.
It’s out now.
It's 404 now
Now I hope that nvidia will host it for free :-)
if it's anything like the speeds Nvidia Nim puts Deepseek at, it'll probably be 10 tok/s or lower and timeout frequently
This is (actually) AGI, that truly benefits all of humanity with zero gatekeeping.
Now the US government has 5 hours left to (attempt to) stop the release. (and save Anthropic)
Let competition run its course and the market (not government) determine the winners and losers.
now, it gives 404 lol :)
[flagged]
[flagged]
[dead]
[flagged]
[dead]
[dead]
Will it work on 4GB of VRAM? /s
[dead]
FYI huggingface refers to the alien from the Aliens movies that we need to prevent from reaching earth at any cost because it means the end of civilization.
Just checking in because y'all sound good with that.
Doesn’t it refer to the emoji?
Those are facehuggers.
haha stupid xenomorphs with their acid blood and pointy bits - all they had to do is make the beasts write code and do our homework :)
When Gen Z is in charge of security protocols, lol.
Funny retcon, but come on… TIL huggingface started as a chatbot for teens who didn’t get enuf hugs.