RX 7900 XTX 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.
RX 7900 XTX can run openai/gpt-oss-20b with Q4 quantization. At approximately 81 tokens/second, you can expect Good speed - acceptable for interactive use.
You have 14GB headroom, which is sufficient for system overhead and smooth operation.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 10GB | 24GB | 80.71 tok/s | ✅ Fits comfortably |
| Q8 | 20GB | 24GB | 55.97 tok/s | ✅ Fits comfortably |
| FP16 | 41GB | 24GB | 28.32 tok/s | ❌ Not recommended |