Hacker News new | ask | show | jobs
by grej 459 days ago
It lasted until Mistral released 3.1 Small a week later. Such is the pace of AI...
2 comments
nirav72 459 days ago
yeah, I can't even keep up these days. So now mainly focus on what I can run locally via Ollama.
link
simonw 459 days ago
Gemma 3 is on Ollama now https://ollama.com/library/gemma3 but surprisingly they don't have Mistral 3.1 yet.

I've managed to run Mistral 3.1 on my laptop using MLX, notes here https://simonwillison.net/2025/Mar/17/mistral-small-31/

link
thot_experiment 459 days ago
Are you running vision tasks? Works just fine in ollama as an LLM but the vision component is unimplemented.
link
pitzips 459 days ago
I'm using gemma3:27b with the latest ollama (0.6.2) and vision is working.
link
thot_experiment 458 days ago
Yes but we're talking about mistral 3.1 here, which doesn't have the vision component implemented, looks like vllm supports it though.
link
simonw 458 days ago
Mistral 3.1 vision works with MLX and mlx-vlm - https://github.com/Blaizzy/mlx-vlm/pull/256

https://huggingface.co/mlx-community/Mistral-Small-3.1-24B-I...

link
lostmsu 459 days ago
How's their lmarena ELO?
link