Directory › Models › Qwen2.5 7B

Qwen2.5 7B

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

Qwen2.5 7B is a strong multilingual model with a permissive Apache-2.0 license.

Who it's for: This tool is suitable for users who require a self-hostable AI solution.

Run it locally

ollama run qwen2.5:7b

Strengths

  • Strong performance
  • Permissive license
  • Self-hostable

Trade-offs

  • Limited data availability
  • No GitHub repository

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 →