Second-generation Devstral Small for agentic coding. Built for tool use to explore codebases, edit multiple files, and power software engineering agents with newly added vision support.
To run the smallest Devstral 2, you need at least 16 GB of RAM.
Devstral 2 models support tool use and vision input. They are available in gguf.

Devstral is an agentic LLM for software engineering tasks. Devstral Small 2 excels at using tools to explore codebases, editing multiple files and power software engineering agents. The model achieves remarkable performance on SWE-bench.
This model is an Instruct model, fine-tuned to follow instructions, making it ideal for chat, agentic and instruction based tasks for SWE use cases.
To use this model in LM Studio, please update your runtime to the latest version by running:
lms runtime update
And then, download the model within the app.
Devstral Small 2 (24B) is 28x smaller than DeepSeek V3.2, and 41x smaller than Kimi K2, proving that compact models can match or exceed the performance of much larger competitors. Their reduced size makes deployment practical on limited hardware, lowering barriers for developers, small businesses, and hobbyists hardware.

Devstral Small 2 scores 68.0% on SWE-bench Verified, and places firmly among models up to five times its size while being capable of running locally on consumer hardware.

Devstral 2 is provided under the Apache 2.0 license.