LocalClaw/LLM/Codestral (22B)
Open-weight local LLM

Codestral (22B)

Mistral's first code model. Supports 80+ programming languages. 476K downloads.

16 GB sweet spot 16 GB RAM Q4_K_M Code generation
Run with LocalClaw Compare all models
Parameters
22B
Minimum RAM
16 GB
Model size
13 GB
Quantization
Q4_K_M

Can Codestral (22B) run locally?

Codestral (22B) is a practical pick for 16 GB machines, especially with Q4_K_M quantization.

Search for codestral-22b-v0.1 in LM Studio or another GGUF-compatible runtime.

lmstudio-community/Codestral-22B-v0.1-GGUF
codepower

Install path

01
Check RAM fitMinimum 16 GB RAM. Start with the Q4_K_M quant.
02
Load the modelSearch codestral-22b-v0.1 in LM Studio.
03
Control locallyUse LocalClaw to manage models, agents, chat, channels and scheduled OpenClaw work.

Strengths

  • Mistral's first code model
  • 80+ languages
  • Strong completion and generation
  • 476K downloads

Limitations

  • Non-production license
  • 32K context
  • Not for commercial use without license

Best use cases

  • Code generation
  • Code completion
  • Refactoring
  • Code review

Capability profile

speed
5
quality
7
coding
9
reasoning
7

Technical notes

Developer
Mistral AI
License
MNPL (Non-Production License)
Context window
32,768 tokens
Architecture
Transformer optimized for code

This model fits these next steps

Hardware fit is based on LocalClaw's RAM tier, model size and quantization metadata. Always leave memory headroom for your OS and runtime.

Starter desktopMac mini M4 16GBPortable fitMacBook Air M4 16GBBest 16GB models16GB RAM guide

Similar models to compare

Qwen 2.5 Coder (32B) 32BDeepSeek Coder (33B) 33BDevstral (24B) 24B

Where to go next