Anyone tested it at high context yet? I find all Mistral models peter out after like 16K-24K tokes no matter what they advertise the context length as.
A GPT-4o-mini comparable system that you can run on a RTX 4090 isn't going to solve direct problems, but it might have enterprise uses. Text generation automation for personal use should be strong, for example - in place of having a third party API do it.
6 Comments
brucethemoose@lemmy.world · 8 pts · 1y
Anyone tested it at high context yet? I find all Mistral models peter out after like 16K-24K tokes no matter what they advertise the context length as.
obbeel@lemmy.eco.br · 6 pts · 1y
A GPT-4o-mini comparable system that you can run on a RTX 4090 isn't going to solve direct problems, but it might have enterprise uses. Text generation automation for personal use should be strong, for example - in place of having a third party API do it.
possiblylinux127@lemmy.zip · 3 pts · 1y
English version: https://mistral.ai/news/mistral-small-3-1
Picasso@sh.itjust.works · 2 pts · 1y
Is this expected to be released on ollama?
kata1yst@sh.itjust.works · 1 pts · 1y
I'm using https://ollama.com/justinledwards/mistral-small-3.1-Q6_K
And it's stunningly good. Absolutely running circles around Gemma 3 and Phi-4
Smokeydope@lemmy.world · 1 pts · 1y
This is so exciting! Glad to see mistral at it with more bangers.