News for hackers. Stuff that matters.

A comment on Mistral CEO confirms 'leak' of new open source AI model nearing GPT4 performance. Parent comment

Re:Mistral CEO confirms 'leak' of new open source AI model n... by lukasm on Thursday February 01, 2024 @06:39AM (#39214889)
Which model is the best to run on M3 max ATM?
[ Parent | on HN ]
Re:Mistral CEO confirms 'leak' of new open source AI model n... by a_wild_dandan on Thursday February 01, 2024 @07:05PM (#39223298)
That depends on your goal and available memory. I generally use Mixtral for text, LlaVA for multimodal stuff, and Copilot in VSCode.
[ Parent | on HN ]