this post was submitted on 14 Jan 2025
34 points (90.5% liked)

Selfhosted

41084 readers
265 users here now

A place to share alternatives to popular online services that can be self-hosted without giving up privacy or locking you into a service you don't control.

Rules:

  1. Be civil: we're here to support and learn from one another. Insults won't be tolerated. Flame wars are frowned upon.

  2. No spam posting.

  3. Posts have to be centered around self-hosting. There are other communities for discussing hardware or home computing. If it's not obvious why your post topic revolves around selfhosting, please include details to make it clear.

  4. Don't duplicate the full text of your blog or github here. Just post the link for folks to click.

  5. Submission headline should match the article title (don’t cherry-pick information from the title to fit your agenda).

  6. No trolling.

Resources:

Any issues on the community? Report it using the report flag.

Questions? DM the mods!

founded 2 years ago
MODERATORS
[email protected]
[email protected]
[email protected]
[email protected]
[email protected]
[email protected]
34
Using Mac M2 Ultra 192GB to Self-Host LLMs? (sh.itjust.works)
submitted 23 hours ago* (last edited 2 hours ago) by [email protected] to c/[email protected]
30 comments fedilink hide all child comments
 

I’m doing a lot of coding and what I would ideally like to have is a long context model (128k tokens) that I can use to throw in my whole codebase.

I’ve been experimenting e.g. with Claude and what usually works well is to attach e.g. the whole architecture of a CRUD app along with the most recent docs of the framework I’m using and it’s okay for menial tasks. But I am very uncomfortable sending any kind of data to these providers.

Unfortunately I don’t have a lot of space so I can’t build a proper desktop. My options are either renting out a VPS or going for something small like a MacStudio. I know speeds aren’t great, but I was wondering if using e.g. RAG for documentation could help me get decent speeds.

I’ve read that especially on larger contexts Macs become very slow. I’m not very convinced but I could get a new one probably at 50% off as a business expense, so the Apple tax isn’t as much an issue as the concern about speed.

Any ideas? Are there other mini pcs available that could have better architecture? Tried researching but couldn’t find a lot

Edit: I found some stats on GitHub on different models: https://github.com/ggerganov/llama.cpp/issues/10444

Based on that I also conclude that you’re gonna wait forever if you work with a large codebase.

you are viewing a single comment's thread
view the rest of the comments
[–] [email protected] 3 points 21 hours ago (1 children)

If you enjoy waiting around, sure

[–] [email protected] 1 points 20 hours ago (1 children)

Meh, ofc I don’t.

[–] [email protected] 2 points 20 hours ago (2 children)

Then don't go with an Apple chip. They're impressive for how little power they consume. But any 50 watt chip will get absolutely destroyed by a 500 watt gpu, even one from almost a decade ago will beat it.

And you'll save money to boot, if you don't count your power bill

[–] [email protected] 6 points 18 hours ago (1 children)

But any 50 watt chip will get absolutely destroyed by a 500 watt gpu

If you are memory-bound (and since OP's talking about 192GB, it's pretty safe to assume they are), then it's hard to make a direct comparison here.

You'd need 8 high-end consumer GPUs to get 192GB. Not only is that insanely expensive to buy and run, but you won't even be able to support it on a standard residential electrical circuit, or any consumer-level motherboard. Even 4 GPUs (which would be great for 70B models) would cost more than a Mac.

The speed advantage you get from discrete GPUs rapidly disappears as your memory requirements exceed VRAM capacity. Partial offloading to GPU is better than nothing, but if we're talking about standard PC hardware, it's not going to be as fast as Apple Silicon for anything that requires a lot of memory.

This might change in the near future as AMD and Intel catch up to Apple Silicon in terms of memory bandwidth and integrated NPU performance. Then you can sidestep the Apple tax, and perhaps you will be able to pair a discrete GPU and get a meaningful performance boost even with larger models.

[–] [email protected] 1 points 8 hours ago (1 children)

Again, you'd be waiting around all day

[–] [email protected] 1 points 1 hour ago* (last edited 1 hour ago)

Yeah I found some stats now and indeed you’re gonna wait like an hour to process if you throw like 80-100k token into a powerful model. With APIs that kinda works instantly, not surprising but just to give a comparison. Bummer.

[–] [email protected] 2 points 18 hours ago (1 children)

The power bill side is also not even clear cut. The longer processing time for slower chips sometimes ends up resulting in higher costs. It's surprisingly not as simple as lower wattage chip is cheaper to operate.

[–] [email protected] 1 points 8 hours ago

Good point!