mistralai/Magistral-Small-2506

Posted by yoracale@reddit | LocalLLaMA | View on Reddit | 151 comments

Building upon Mistral Small 3.1 (2503), with added reasoning capabilities, undergoing SFT from Magistral Medium traces and RL on top, it's a small, efficient reasoning model with 24B parameters.

Magistral Small can be deployed locally, fitting within a single RTX 4090 or a 32GB RAM MacBook once quantized.

Learn more about Magistral in Mistral's blog post.

Key Features

Benchmark Results

Model AIME24 pass@1 AIME25 pass@1 GPQA Diamond Livecodebench (v5)
Magistral Medium 73.59% 64.95% 70.83% 59.36%
Magistral Small 70.68% 62.76% 68.18% 55.84%