mistral-7b-instruct feels like chatgpt, its running fast on my macbook, and its only a 5GB model. Wow!

https://cdn.jb55.com/s/9d74cabac4f4c15f.txt

Reply to this note

Please Login to reply.

Discussion

Have you tried llava? I’m amazed by how it runs on my 16GB Mac under ollama.ai.

https://llava-vl.github.io/

Not yet!

The smaller the model, the faster it will run.

ollama is also good. i think it is using GPU better than llama.cpp.

You can also run mistral-7b on iOS:

https://apps.apple.com/gb/app/mlc-chat/id6448482937