Modelofficial release

mistralai/Magistral-Small-2509

Mistral models →Hugging Face ↗

Parameters24B

Context128K

Input → output–

Licenseapache-2.0

PrecisionBF16

ArchitectureMistral3ForConditionalGeneration

ReleasedSep 12, 2025

Downloads6.7K

Based on mistralai/Mistral-Small-3.2-24B-Instruct-2506

Other sizes and formats in the family

Model	Params	Precision	Downloads
mistralai/Magistral-Small-2509-GGUFgguf	–	–	5.1K

Compare side by side →

Built on this model

Model	Params	Precision	Downloads
mistralai/Magistral-Small-2509-GGUFgguf	–	–	5.1K

This release in the news

No coverage of this exact release yet.

Recent news about Mistral models

Oct 11, 2026 · Opinion / analysis
Local Voice Assistant based on Qwen3.5 4B with skills/toolcalling. No dedicated GPU. Local STT+TTS
Oct 10, 2026 · Research paper
Sharing AI progress in mathematics
Oct 8, 2026 · Model release
mistralai/Voxtral-Mini-4B-Realtime-Arabic
Oct 7, 2026 · Product / feature launch
Introducing Mistral Large 4
Oct 7, 2026 · Research paper
Activation-Aware Weight Tensorization: A Calibration-Time Preconditioner for Tensor-Network LLM Compression
Oct 6, 2026 · Model release
llm-mistral 0.16
Oct 6, 2026 · Opinion / analysis
Mistral Large 4
Oct 6, 2026 · Research paper
One Step at a Time: Trading LLM Autonomy for Process Predictability