Back to Models
ChatApache 2.0Open weights

Mistral Small 3.1

Mistral AI · Mistral

Efficient open-weight Mistral-family model often considered for practical local chat and app workloads.

Best for

Builders who want a smaller capable model with permissive licensing and good local runtime support.

Tradeoffs

May not match larger MoE models on hard reasoning; compare on your own prompts before production.

Local hardware notes

24B-class models are realistic on higher-end local systems with quantization.

Local workflow notes

A practical local candidate when quantized; still test memory use and context length on your hardware.

Local runtimes: Ollama, LM Studio, llama.cpp, vLLM

Platforms: Windows, macOS, Linux

Hardware16GB+ quantizedRuntimeOllama, LM Studio, llama.cpp, vLLMContextCheck current Mistral model cardUpdated2026
Mistral model card