# Can I run Qwen3 235B A22B on Apple M4 Max (128GB)?

Updated: 2026-06-15

**No, not enough memory.** Needs ~136.9 GB even at Q4_K_M, but only ~96 GB is usable.

- Model: 235B (MoE, 22B active), Q4_K_M 132.39 GB
- Device: 128 GB unified, ~96 GB usable for weights
- Needs ~136.9 GB at Q4_K_M; recommended quant: n/a
- Best tool on macOS: LM Studio
- Command: `ollama run qwen3:235b`

Estimate. Method: weights + KV cache + ~0.8GB overhead. Sources: https://ollama.com/library/qwen3, https://ollama.com/library/qwen3/tags, https://huggingface.co/unsloth/Qwen3-235B-A22B-GGUF, https://huggingface.co/Qwen/Qwen3-235B-A22B.

More: https://localmodel.run/can-i-run/qwen3-235b-a22b/apple-m4-max-128gb