Apple M4 Pro meets the minimum VRAM requirement for Q4 inference of Qwen/Qwen3-Next-80B-A3B-Instruct-FP8. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.
Apple M4 Pro can run Qwen/Qwen3-Next-80B-A3B-Instruct-FP8 with Q4 quantization. At approximately 8 tokens/second, you can expect Low speed - consider quantization or stronger GPU.
You have 25GB headroom, which is sufficient for system overhead and smooth operation.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 39GB | 64GB | 8.04 tok/s | ✅ Fits comfortably |
| Q8 | 78GB | 64GB | 5.51 tok/s | ❌ Not recommended |
| FP16 | 156GB | 64GB | 2.82 tok/s | ❌ Not recommended |