Welcome to LocalLLaMA! Here we discuss running and developing machine learning models at home. Lets explore cutting edge open source neural network technology together.
Get support from the community! Ask questions, share prompts, discuss benchmarks, get hyped at the latest and greatest model releases! Enjoy talking about our awesome hobby.
As ambassadors of the self-hosting machine learning community, we strive to support each other and share our enthusiasm in a positive constructive way.
Rules:
Rule 1 - No harassment or personal character attacks of community members. I.E no namecalling, no generalizing entire groups of people that make up our community, no baseless personal insults.
Rule 2 - No comparing artificial intelligence/machine learning models to cryptocurrency. I.E no comparing the usefulness of models to that of NFTs, no comparing the resource usage required to train a model is anything close to maintaining a blockchain/ mining for crypto, no implying its just a fad/bubble that will leave people with nothing of value when it burst.
Rule 3 - No comparing artificial intelligence/machine learning to simple text prediction algorithms. I.E statements such as "llms are basically just simple text predictions like what your phone keyboard autocorrect uses, and they're still using the same algorithms since <over 10 years ago>.
Rule 4 - No implying that models are devoid of purpose or potential for enriching peoples lives.
32 GB VRAM for less $1k sounds like a steal these days, and I'm sure it's not getting cheaper any time soon.
Does anyone here use this GPU? Or any recent Arc Pros? I basically want someone to talk me out of driving to the nearest place that has it in stock and getting $1k poorer.
Thanks! I was running some models on my RX 9070XT, but only Ollama works flawlessly. I couldn't make llama.Cpp to run Gemma4 or the newer Qwen - maybe I'm hitting that incompatibility, but probably it's the skill issue.
P40 doesn't look very appealing. 32 GB V100 costs about the same as 2xP40, less VRAM in total, but it's faster, will use less power.
But I'm not sure if I follow you on the PCIe... If I run a model that spans multiple GPUs, doesn't PCIe bandwidth matter?
It matters a bit but not as much as you'd think, it also depends on what model and what runner you're using I think. There's a lot of optimizing that can be done, but in practice, you're not going to notice huge difference in speed. Again, remember that these are not speed-demon cards to begin with, the main feature is the large VRAM capacity that allows them to run very large, powerful models without the speed penalty of dropping to system RAM, and that, at least where I understand it, is where the PCIe starts to matter a lot more. That said, maybe I'm wrong. I'm not an expert at this stuff and my experience is limited to what little hardware in what limited configurations I have available personally. Best of luck in your adventures, anything we can do to democratize machine learning technology to more people is worth pursuing I think.