# Can I run Qwen2.5 72B on Apple M5 Max (128GB)?

Updated: 2026-06-15

**Yes, it runs.** Runs at Q4_K_M using ~50.2 GB of ~96 GB usable. You have room for Q8_0 for higher quality.

- Model: 72B, Q4_K_M 47.42 GB
- Device: 128 GB unified, ~96 GB usable for weights
- Needs ~50.2 GB at Q4_K_M; recommended quant: Q4_K_M
- Best tool on macOS: LM Studio
- Command: `ollama run qwen2.5:72b`

Estimate. Method: weights + KV cache + ~0.8GB overhead. 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/can-i-run/qwen2.5-72b/apple-m5-max-128gb