Local LLM model page

Mistral Small (24B)

Mistral's refined 24B model. Excellent for nuanced conversations and professional writing.

Find the best model for my hardwareBrowse all 183 LLMs
Parameters
24B
Minimum RAM
24 GB
Model size
15 GB
Quantization
Q4_K_M

Can Mistral Small (24B) run locally?

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

Search term for LM Studio or compatible runtimes: mistral-small-24b-instruct

Hugging Face repository: lmstudio-community/Mistral-Small-24B-Instruct-2501-GGUF

chatgeneralpowerquality

Strengths

  • Excellent quality-to-size ratio
  • Strong European multilingual
  • Apache 2.0
  • Fast inference for 24B

Limitations

  • 32K context limit
  • Needs 16GB+ RAM

Best use cases

  • Enterprise chatbot
  • Multilingual support
  • Professional writing
  • Code generation

Benchmarks

Speed: 5/10

Quality: 8/10

Coding: 7/10

Reasoning: 8/10

Technical details

Developer: Mistral AI

License: Apache 2.0

Context window: 32,768 tokens

Architecture: Transformer decoder-only

Released: 2025-01

Similar models

gemma3-27bqwen3-32bcodestral-22b