News for hackers. Stuff that matters.

A comment on Mistral Releases Devstral 2 (72.2% SWE-Bench Verified) and Vibe CLI. Parent comment

Re:Mistral Releases Devstral 2 (72.2% SWE-Bench Verified) an... by chrsw on Tuesday December 09, 2025 @01:08PM (#46208293)
> run locally for agentic coding. Nowadays I mostly use GPT-OSS-120b for this

What kind of hardware do you have to be able to run a performant GPT-OSS-120b locally?

[ Parent | on HN ]
Re:Mistral Releases Devstral 2 (72.2% SWE-Bench Verified) an... by embedding-shape on Tuesday December 09, 2025 @02:11PM (#46209191)
RTX Pro 6000, ends up taking ~66GB when running the MXFP4 native quant with llama-server/llama.cpp and max context, as an example. Guess you could do it with two 5090s with slightly less context, or different software aimed at memory usage efficiency.
[ Parent | on HN ]
Re:Mistral Releases Devstral 2 (72.2% SWE-Bench Verified) an... by kristianp on Tuesday December 09, 2025 @05:06PM (#46211406)
That has 96GB GDDR7 ECC, to save people looking it up.
[ Parent | on HN ]
Re:Mistral Releases Devstral 2 (72.2% SWE-Bench Verified) an... by fgonzag on Tuesday December 09, 2025 @02:04PM (#46209115)
The model is 64GB (int4 native), add 20GB or so for context.

There are many platforms out there that can run it decently.

AMD strix halo, Mac platforms. Two (or three without extra ram) of the new AMD AI Pro R9700 (32GB of RAM, $1200), multi consumer gpu setups, etc.

[ Parent | on HN ]
Re:Mistral Releases Devstral 2 (72.2% SWE-Bench Verified) an... by FuckButtons on Tuesday December 09, 2025 @04:01PM (#46210593)
Mbp 128gb.
[ Parent | on HN ]