this post was submitted on 23 Nov 2023
1 points (100.0% liked)

LocalLLaMA

3 readers
1 users here now

Community to discuss about Llama, the family of large language models created by Meta AI.

founded 1 year ago
MODERATORS
communick@poweruser.forum
1
The Acer Intel A770 16GB GPU is now $250. You won't find a better new 16GB GPU for less. (alien.top)
submitted 11 months ago by fallingdowndizzyvr@alien.top to c/localllama@poweruser.forum
22 comments fedilink hide all child comments
 

Amazon has the Acer A770 on sale for $250. That's a lot of compute with 16GB of VRAM for $250. There is no better value. It does have it's challenges. Somethings like MLC Chat run with no fuss just like on any other card. Other things need some effort like Oob, Fastchat and BigDL. But support for it is getting better and better everyday. At this price, I'm tempted to get another. I have seen some reports of running multi-GPU setups with the A770.

It also comes with Assassins Mirage for those people that still use their GPUs to game.

https://www.amazon.com/dp/B0BHKNK84Y

you are viewing a single comment's thread
view the rest of the comments
[–] CheatCodesOfLife@alien.top 1 points 11 months ago (1 children)

I'm finding I prefer llama.cpp now as well (the last few days), though for work I usually use Oob + gptq.

If you have it handy, could you post the compile command you used to get llamacpp built for the A770?

[–] fallingdowndizzyvr@alien.top 1 points 11 months ago (1 children)

It's just the normal OpenCL and Vulkan compile flags. So "make LLAMA_CLBLAST=1" and "make LLAMA_VULKAN=1". You will have to download the Vulkan PR for Vulkan. Bu as I said, it's painfully slow. Like slower than the CPU. So not worth it. Both are equally as slow so there seems to be something in common that is not A770 friendly. Although I haven't tried Vulkan in a couple of weeks so that might be better. I even tried giving it the Intel specific OpenCL more than 4GB option but that didn't make any difference at all.

[–] CheatCodesOfLife@alien.top 1 points 11 months ago (1 children)

Right. Kind of feels like Intel are leaving money on the table by not writing software for this lol

[–] fallingdowndizzyvr@alien.top 1 points 11 months ago

They did. That's why software that uses Pytorch like FastChat and SD work very well with Intel Arc. But llama.cpp doesn't use Pytorch.

Here's the base of their software. An API that they are pushing as a standard since it also supports nvidia and AMD as well.

https://www.oneapi.io/

Also, Intel has their own package of LLM software.

https://github.com/intel-analytics/BigDL