Apple M4 Pro meets the minimum VRAM requirement for Q4 inference of openai/gpt-oss-120b. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.
Apple M4 Pro can run openai/gpt-oss-120b with Q4 quantization. At approximately 7 tokens/second, you can expect Low speed - consider quantization or stronger GPU.
You have 5GB headroom, which is sufficient for system overhead and smooth operation.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 59GB | 64GB | 6.91 tok/s | ✅ Fits comfortably |
| Q8 | 117GB | 64GB | 4.77 tok/s | ❌ Not recommended |
| FP16 | 235GB | 64GB | 2.77 tok/s | ❌ Not recommended |