Apple M3 Pro meets the minimum VRAM requirement for Q4 inference of Qwen/Qwen2.5-72B-Instruct. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.
Apple M3 Pro can run Qwen/Qwen2.5-72B-Instruct with Q4 quantization. At approximately 4 tokens/second, you can expect Low speed - consider quantization or stronger GPU.
VRAM usage will be very close to your GPU's limit. Consider closing other applications or using Q3 quantization for more margin.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 35GB | 36GB | 3.84 tok/s | ⚠️ Tight fit |
| Q8 | 70GB | 36GB | 2.65 tok/s | ❌ Not recommended |
| FP16 | 141GB | 36GB | 1.54 tok/s | ❌ Not recommended |