Loading content...
Loading GPU benchmarks...
AMD Instinct MI250X meets the minimum VRAM requirement for Q4 inference of openai/gpt-oss-20b. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 10GB | 128GB | 277.78 tok/s | ✅ Fits comfortably |
| Q8 | 20GB | 128GB | 190.07 tok/s | ✅ Fits comfortably |
| FP16 | 41GB | 128GB | 97.87 tok/s | ✅ Fits comfortably |