Local LLM model page

Mistral 7B v0.3

The legendary Mistral. Still incredibly fast and reliable for everyday tasks.

Find the best model for my hardwareBrowse all 183 LLMs
Parameters
7B
Minimum RAM
8 GB
Model size
5 GB
Quantization
Q5_K_M

Can Mistral 7B v0.3 run locally?

Mistral 7B v0.3 is best suited for entry-level laptops and desktops. LocalClaw recommends Q5_K_M as the default quantization, with at least 8 GB RAM.

Search term for LM Studio or compatible runtimes: mistral-7b-instruct-v0.3

Hugging Face repository: lmstudio-community/Mistral-7B-Instruct-v0.3-GGUF

chatgeneralstandard

Strengths

  • The legendary Mistral
  • Apache 2.0
  • Great speed
  • Huge community

Limitations

  • Surpassed by newer models
  • 32K context
  • Weaker at coding

Best use cases

  • General chat
  • Quick tasks
  • Fine-tuning base
  • RAG

Benchmarks

Speed: 8/10

Quality: 6/10

Coding: 6/10

Reasoning: 5/10

Technical details

Developer: Mistral AI

License: Apache 2.0

Context window: 32,768 tokens

Architecture: Transformer with Sliding Window Attention + GQA

Released: 2024-05

Similar models

llama3.1-8bqwen2.5-7bgemma2-9b