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 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 ]