---
title: "Mistral Small — LLM profile"
provider: "Mistral AI"
version: "small"
model_type: "llm"
context_window: "128000"
url: "https://lforla.org/models/mistral-small"
markdown_twin: "https://lforla.org/markdown/models/mistral-small.md"
---
# Mistral Small

Mistral Small, optimized for low-latency inference