Comment by utopiah
6 hours ago
> suddenly jack up the rates or go out of business?
There is basically no lock-in, you don't even "move" your image, your data is basically some "context" or a history of prompts which probably fits in a floppy disk (not even being sarcastic) so if you know the basic about containerization (Docker, podman, etc) which most likely the cloud provider even takes care of, then it takes literally minutes to switch from one to another. It's really not more complex that setting up a PHP server, the only difference is the hardware you run on and that's basically a dropdown button on a Web interface (if you don't want to have scripts for that too) then selecting the right image (basically NVIDIA support).
Consequently even if that were to happen (which I have NEVER seen! at worst it's like 15% increase after years) then it would actually not matter to you. It's also very unlikely to happen based of the investment poured into the "industry". Basically everybody is trying to get "you" as a customer to rely on their stack.
... but OK, let's imagine that's not appealing to you, have you not done the comparison of what a Mac Studio (or whatever hardware) could actually buy otherwise?
Ok. I think I misunderstood. So the idea is to simple set up the LLM service on the server and access it with an API like I would with any LLM provider? This way whatever application I want to use it for stays at home?
That's a bit more appealing. How much would it cost per month to have it continually online?
Well it depends entirely on what you need. You can even do the training yourself on that infrastructure to rent if you want. The more you do yourself, the more private but also the more expensive it will be.
I don't want to make an ad here but I'm going to point to HuggingFace https://endpoints.huggingface.co (and to avoid singling them out just https://replicate.com/pricing too but I don't know them well) as an example with pricing.
The "beauty" IMHO of such solutions is that again you pay for what you want. If you want to use the endpoint only for 5min to test that the model and its API fits your need? OK. You want the whole month? Sure. You want 1 user, namely you? Fine, not a lot of power, you want your whole organization to use that endpoint? Scale up.
I'm going to give very rough approximation because honestly I'm not really into this so someone please adjust with source :
Apple Mac Studio M3 Ultra 96GB = $4K
~NVIDIA A100 with 80G ~ 10x perf compared to M3 Pro (obviously depends on models)
So on Replicate today a one can get an A100 for ~$5/hr which is ... about a month. But that's for 10x speed and electricity included. So very VERY approximately if you use a Mac Studio for 10 months on AI non stop (days and night) then it's arguably worth it.
If you use it less, say 2hrs/day only for inference, then I imagine it takes few years to have the equivalent and by that time I bet Replicate or HuggingFace is going to rent much faster setup for much cheaper simply because that's what they have ALL done for the last few years.
Well, full disclosure (despite my comments above): I'm not interested in buying a Mac Studio. I was merely explaining why I thought people may prefer it.
For my own use, I'm just looking at absolute price (and convenience).
I haven't explored open weights models, so I have no idea which I'd want. It would be great to get a "frontier" model like Minimax-M2.5, but at $10/hr, it's not worth it - let alone $40/hr for GLM-5. I'd have to explore use cases for cheaper models. Likely for things related to reading emails, I can get by with a much cheaper model.
If I set one of these up, how easily is it for me to launch one of these (on the command line on my home PC) and then shut it down. Right now, when I write any app (or use OpenCode), it's frictionless. My worry is that either turning it on will be a hassle, and even worse, I'll forget to turn it off and suddenly get a big pointless bill.
If there are any guides out there on how people manage all this, it would be much appreciated.
1 reply →