[mlboss]

Is it possible to run the smallest one on a consumer gpu with 24gb ram ?

[MacsHeadroom]

You can do even better!. You can run the second smallest one (better than GPT-3 175B) on 24GB of vram, ie LLaMA-13B. https://github.com/oobabooga/text-generation-webui/issues/14...

[Tepix]

Running it is easy but you'll probably want to finetune it, too

[rihegher]

I would be surprised if you can't. The smallest weight file is 14gb apparently

[eightysixfour]

https://github.com/facebookresearch/llama/blob/main/FAQ.md#3

Looks like it needs 14gb for weights and it isn't clear what the minimum size for the decoding cache is, but it defaults to settings for 30gb GPUs.

[MacsHeadroom]

In int8 7B needs only 9GB of VRAM and 13B needs only 20GB on a single GPU. https://github.com/oobabooga/text-generation-webui/issues/14...