# Qwen2.5 72B requirements

Updated: 2026-06-15

Qwen2.5 family, 72B params, released 2024-09.

- Q4_K_M: 47.42 GB on disk; ~50.2 GB to run at 4k context
- Q8_0: 77.26 GB
- Context: 128k
- Run: `ollama run qwen2.5:72b`
- Runs on 3 of 39 tracked devices

Sources: https://ollama.com/library/qwen2.5, https://huggingface.co/bartowski/Qwen2.5-72B-Instruct-GGUF, https://qwenlm.github.io/blog/qwen2.5/, https://lmarena.ai/leaderboard
More: https://localmodel.run/model/qwen2.5-72b