AMD Instinct MI250X 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.
AMD Instinct MI250X can run mlx-community/gpt-oss-20b-MXFP4-Q8 with Q4 quantization. At approximately 288 tokens/second, you can expect Excellent speed - conversational response times under 1 second.
You have 118GB headroom, which is sufficient for system overhead and smooth operation.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 10GB | 128GB | 288.22 tok/s | ✅ Fits comfortably |
| Q8 | 20GB | 128GB | 190.68 tok/s | ✅ Fits comfortably |
| FP16 | 41GB | 128GB | 99.35 tok/s | ✅ Fits comfortably |