Local LLM model page

Devstral (24B)

Best open model for coding agents. Designed for agentic coding workflows. 391K downloads.

Find the best model for my hardware Browse all 183 LLMs

Parameters

24B

Minimum RAM

20 GB

Model size

14 GB

Quantization

Q4_K_M

Can Devstral (24B) run locally?

Devstral (24B) is best suited for power-user machines with 32 GB RAM. LocalClaw recommends Q4_K_M as the default quantization, with at least 20 GB RAM.

Search term for LM Studio or compatible runtimes: devstral-24b

Hugging Face repository: mistralai/Devstral-Small-2507-GGUF

codepower

Strengths

Best open model for coding agents
Apache 2.0
128K context
Designed for agentic workflows

Limitations

Needs 20GB+ RAM
Coding specialist — limited general chat

Best use cases

Agentic coding
Automated software development
Code review
Complex refactoring

Benchmarks

Speed: 5/10

Quality: 8/10

Coding: 10/10

Reasoning: 8/10

Technical details

Developer: Mistral AI

License: Apache 2.0

Context window: 131,072 tokens

Architecture: Transformer optimized for agentic coding

Released: 2025-07