Directory › Models › Mistral 7B

Mistral 7B

Models ✓ verified 🔒 local-only Apache-2.0
HuggingFace ↗ Website ↗ Ollama ↗

Mistral 7B is a permissively-licensed 7B model used as a local baseline. It is an AI tool.

Who it's for: This model is suitable for users who require a locally hosted, efficient 7B model.

Run it locally

ollama run mistral:7b

Strengths

  • Efficient
  • Permissively-licensed
  • Widely used

Trade-offs

  • Limited availability of source code
  • No specific information on performance or benchmarks

Data locality

Runs fully offline — no data leaves your machine.

Hardware estimate

7.0B params · ~6.0 GB VRAM at Q4_K_M (estimate). Check your machine →