RUN THIS LLM

Search local LLM hardware requirements

← Back to all models

Devstral 2 123B

Mistral · 123B · Code

Large agentic coding model. State-of-the-art open-weights SWE-Bench performance at release. 256K context.

VRAM Requirements

QuantizationVRAM
Q4_K_M (smallest)73.8 GB
Q8_0 (balanced)135.3 GB
FP16 (full quality)246 GB

Specifications

Loading interactive analysis...

RTL
Add Run This LLM to your home screen
Get the Chrome Extension
Look up hardware requirements for any model right from your browser sidebar — no tab switching needed.
Add to Chrome — It's Free