mistralai/Devstral-2-123B-Instruct-2512
Parameters125B
Context256K
Input → output–
Licenseother
PrecisionF8_E4M3 · fp8
ArchitectureMinistral3ForCausalLM
ReleasedNov 28, 2025
Downloads6K
This release in the news
No coverage of this exact release yet.
Recent news about Mistral models
- Oct 11, 2026 · Opinion / analysisLocal Voice Assistant based on Qwen3.5 4B with skills/toolcalling. No dedicated GPU. Local STT+TTS
- Oct 10, 2026 · Research paperSharing AI progress in mathematics
- Oct 8, 2026 · Model releasemistralai/Voxtral-Mini-4B-Realtime-Arabic
- Oct 7, 2026 · Product / feature launchIntroducing Mistral Large 4
- Oct 7, 2026 · Research paperActivation-Aware Weight Tensorization: A Calibration-Time Preconditioner for Tensor-Network LLM Compression
- Oct 6, 2026 · Model releasellm-mistral 0.16
- Oct 6, 2026 · Opinion / analysisMistral Large 4
- Oct 6, 2026 · Research paperOne Step at a Time: Trading LLM Autonomy for Process Predictability