Apple M4 Pro meets the minimum VRAM requirement for Q4 inference of mlx-community/gpt-oss-20b-MXFP4-Q8. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.
Apple M4 Pro can run mlx-community/gpt-oss-20b-MXFP4-Q8 with Q4 quantization. At approximately 20 tokens/second, you can expect Basic speed - best for non-interactive tasks.
You have 54GB headroom, which is sufficient for system overhead and smooth operation.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 10GB | 64GB | 19.96 tok/s | ✅ Fits comfortably |
| Q8 | 20GB | 64GB | 14.23 tok/s | ✅ Fits comfortably |
| FP16 | 41GB | 64GB | 6.98 tok/s | ✅ Fits comfortably |