Comment by jacquesm
8 hours ago
Working on a blog post to document it all, but that will take a few more days. The short version: the big rig is probably $25K, ttft is dependent on how much prefill you have but typically a couple of seconds (2K prefill/sec in one setup, about 500 in the other), tgs 100 to 150 or so depending on what it is doing and how well the speculative decoder works with the current context. Electricity is pretty bad, full tilt it's about 2500W or so but I've power limited it to 1500 to keep it civil. It is not cheaper than using a frontier lab (or at least, I don't think it is), but the independence bit is the important part for me and I don't care if that carries a surcharge, even if it is a substantial one.
I'm not saying your approach is wrong - but for my workloads, it makes a lot more sense to just pay for a decade (!!!) of Claude Code 20x Max.
My local model never says no. I never get banned. If I want to do security stuff, reverse engine, there it goes! Do I wanna chat about politics? No problem! Do I want it to analyze medical stuff? I don't get to hear that it's not a doctor and I should call 911. Do I want to explore legal docs, no problem! There are lots of things that cloud models will say no to! I read that don't even agree to help with advanced biology and chemistry topic much. I also never run out of tokens, no 5 hr limit. I can run it 24/7. I don't run out of tokens. I can run 16 sub agents at the same time, non stop! 1-4 billion tokens a month? No problem. Any agent harness I want! No restrictions. Privacy all day. My own true system prompt, not something someone has determined, no filters. Furthermore, there are many open weight cloud models that don't have equivalent online. For a while before cloud models got good at math, the best model at math was DeepSeekv2 Math and there was no API. The only way to use it was to run local. All sorts of audio models, image/video models, etc. No multiple subscription needed. Private UI for my family, kids included (I can guard what kids infer). Got a friend that really needs some tokens? I give em access through private VPN. Telling someone that they are paying for decades of Claude for local AI is like telling someone they are paying for decades of public transport when they buy a car. Sure, you are right, but ...
Also no political censorship, and it doesn’t report you to the police when it suspects you did something illegal. That really happened, by the way.
Now I want a local LLM server :( $25k is just so much money.
12 replies →
> My local model never says no.
> I don't get to hear that it's not a doctor and I should call 911.
https://en.wikipedia.org/wiki/Darwin_Awards
1 reply →
Exactly, that's the spirit. I pool the resources with some friends as well.
> My local model never says no. I never get banned.
So much this. Plus everything else you mentioned. The freedom and control is real.
isn't it the same using the same model you host locally but through a cloud provider? does the $ math favour a local setup then?
I think both of y’all glossed over the $25k of it all pretty quickly. This isn’t remotely an option for anyone.
6 replies →
>I don't get to hear that it's not a doctor and I should call 911.
Local models can do this and with tool use they can even call emergency services for you on your behalf.
If I want to go out of business that is what I would do. Most of the data I have here could never be shipped to a service provider, I'd be in lawsuits for the next decade or so and die bankrupt.
That NDA case is the real argument, more than price. Token prices keep dropping anyway, but "this data can never leave the building" doesn't change with a price cut ;)
Okay man I've got to ask, what kind of data are we talking about? Legal? Medical?
I've heard that there are legal software platforms like Clio that offer AI products, not sure what just eavesdropping on some lawyers at the bar.
6 replies →
LLM subscriptions are heavily subsidized. I’d be surprised if Claude 20x costed the same after a decade.
Inference prices are going only down. It could be that some top subscription costs more in a decade, but I fully believe a full array of competent models will be extremely cheap.
The inference is profitable. It’s the training which is really expensive and not being reflected in the subscription prices.
Doesn't deepseek make $38 per GPU-hour? As in they can actually serve profitably?
3 replies →
I was thinking the economics of it the same way.. if the AI companies are burning debt and VC money to give me cheaper tokens why not take them for it? I can always rent a GPU server for those personal, private AI needs.. heck even run a decision model to route them to the rented GPU servers either on demand or scheduled for few hours in a day…
It doesn’t have to be black or white…
For my toy projects, adventures, learning exercises, and throwaway MVPs I will prefer the subscription plans… they are cheap for what they offer today.
From this article alone it should be obvious that the long-repeated myth about frontier inference being subsidized is just that: a myth.
It's training and tuning new models that cost them money. And that's why they are trying to scare people into thinking AI will kill us all in the next 5 years; they want bans on the open-weight models because they know they won't be able to compete with them.
2 replies →
Yeah, the way I see it short term is take the free/subsidized tokens while we can and the further out we go the cheaper compute will get for local setups.
Keep in mind that the prices of the big AI companies are currently mostly loss makers. Their plan is to get sufficient market saturation and dependency of their clients and if they achieve that, they will hike up the prices quite a bit.
(Of course this all depends on if their plans work out, but if not then the smaller local models will probably play a big role in the failure of their plan)
People keep repeating this, but it is only remotely close to true for the literal free plans and the small subset of consumers maxing out the pro plans.
At API pricing (i.e. what all enterprise customers are paying), inference is profitable, even if they're paying usurious rates on cost of capital for capex. Where the frontier labs are getting screwed is that they're in a Red Queen's race with each other, spending tens of billions of dollars per year training the next frontier model, and not being able to recoup the investment on that model before it's obsolete.
That's why you see the CEOs calling for government intervention to "pace the frontier": it lets them reduce investment on training without risking that their competitors keep going and make them obsolete. Unfortunately for them, the Chinese labs exist, and would love nothing more than to take the frontier, so they're in a bit of a pickle.
3 replies →
But what if you become unable to pay for it ? What if:
- they raise the prices 10x
- go bankrupt
- ban you or your country
- decide not to help you with what you want to do for opaque reasons
- you are in jail because the model halucinated something and the company promptly reported you to the police
Better avoid all off these and go local IMHO.
This trope minimizes so many downsides of "frontier" models. When you can't do what you need to with a model it really isn't valuable - which is why subscriptions still exist. As soon as you're forced to pay actual token costs people who keep saying this will likely wish they had invested in something else earlier.
It's also very clear that providers are running variants of models, especially at the SotA levels. I wouldn't be surprised to find out at some point that 1-2 months after release OAI and Anthropic just run "good enough" quants to save themselves on inference (since they're losing money hand over fist). Another upside of local models is that I don't need to worry about model degradation at any given point.
If you compare to API prices the value difference is not as big.
The anthropic sub is likely still subventioned with VC money. So this may not even be available in 2 years.
But yeah, with current sub prices/budget... It's hard to go with anyone else unless you're rich.
Do you take into account the token allowance? For a heavy user this would be the equivalent of many subscriptions and they add up.
If you compare to API prices the value difference is not as big.
The anthropic sub is likely still subventioned with VC money. So this may not even be available in 2 years.
But yeah, with current sub prices/budget... It'd stick with it too
The bet we (self-hosters) are making is that once these companies IPO, they will be forced to do whatever they have to do to make money. i.e. price increases, more throttling of subscription non-usage-based accoutns, etc.
They are subsidizing all of us to the tune of $billions in losses per month. That can't go on for a decade. Probably not even for another 18 months.
I still use all the tokens Claude will give me on the max plan. But I also run deepseek v4 locally for overflow and for... contingencies.
> The bet we (self-hosters) are making is that once these companies IPO, they will be forced to do whatever they have to do to make money. i.e. price increases, more throttling of subscription non-usage-based accoutns, etc.
But, there is no need to make that bet - when prices increase, I'd look into renting a previous-gen GPU on a cloud provider. If the online GPU providers raise prices, then I would look into purchasing for on-site.
Until that happens, I'm not making any bets, because if all the token providers go bust GPU rentals are going to fall in price, and if they don't go bust after raising prices, I can still get years of GPUs for self-hosting at the price of a self-owned rig.
If you know you will pay Claude a few thousand bucks a year a decade adds up too, owning the hardware could just as well end up cheaper because you can sell it or as others have alluded the price to rent could get much worse.
Would you really expect to be using the same hardware over the course of that decade? One of the biggest drawbacks to using on-prem hardware is keeping up with the upgrades. Leasing upgrade cycles are a thing for businesses, but for someone at home it seems like later in the decade the local system will be showing its age.
1 reply →
Heh, the hardware I bought I could easily sell for 2x so you may actually end up making money. Though I hope that that won't last.
The benefit of the agent working firstly for you rather than for Anthropic or OpenAI will become increasingly apparent. We're already seeing signs: remember when Anthropic openly promised to have Claude sabotage people using it to create competitors? And OpenAI is looking for revenue opportunities from advertising, which can't end well for their users.
Just think of how user-hostile other online services have gotten, and imagine how acutely painful the proprietary LLM providers could make theirs. Thankfully, open models provide some counterbalance.
Would you use hosted models if they promised anonymity and no log retention and servers were physically located inside jurisdictions that respect privacy (Switzerland, Norway or similar, I'm not into law) if that meant better price/performance ratio than your current rig?
> It is not cheaper than using a frontier lab
Are you comparing to subscription prices or API prices? Because if it's the former it won't last forever.
True, they're subsidized, I'm not. But I don't have their utilization so I figure it would always be more expensive to run this locally.
Did you get insurance on all this stuff? I imagine home insurance would not qualify for a bespoke home-datacenter.