AMD Instinct MI300X 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 MI300X can run mlx-community/gpt-oss-20b-MXFP4-Q8 with Q4 quantization. At approximately 389 tokens/second, you can expect Excellent speed - conversational response times under 1 second.
You have 182GB headroom, which is sufficient for system overhead and smooth operation.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 10GB | 192GB | 388.96 tok/s | ✅ Fits comfortably |
| Q8 | 20GB | 192GB | 302.29 tok/s | ✅ Fits comfortably |
| FP16 | 41GB | 192GB | 160.01 tok/s | ✅ Fits comfortably |