Apple M4 Max meets the minimum VRAM requirement for Q4 inference of Qwen/Qwen2.5-Math-72B-Instruct. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.
Apple M4 Max can run Qwen/Qwen2.5-Math-72B-Instruct with Q4 quantization. At approximately 15 tokens/second, you can expect Basic speed - best for non-interactive tasks.
You have 92GB headroom, which is sufficient for system overhead and smooth operation.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 36GB | 128GB | 14.90 tok/s | ✅ Fits comfortably |
| Q8 | 71GB | 128GB | 10.04 tok/s | ✅ Fits comfortably |
| FP16 | 142GB | 128GB | 5.22 tok/s | ❌ Not recommended |