RX 7700 XT 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 7700 XT can run openai/gpt-oss-20b with Q4 quantization. At approximately 37 tokens/second, you can expect Moderate speed - useful for batch processing.
VRAM usage will be very close to your GPU's limit. Consider closing other applications or using Q3 quantization for more margin.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 10GB | 12GB | 36.92 tok/s | ✅ Fits comfortably |
| Q8 | 20GB | 12GB | 26.78 tok/s | ❌ Not recommended |
| FP16 | 41GB | 12GB | 13.01 tok/s | ❌ Not recommended |