Mlx Community Gpt Oss 20B Mxfp4 Q8 speed on RX 7900 XTX and quantization-level VRAM fit.
RX 7900 XTX 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.
RX 7900 XTX can run Mlx Community Gpt Oss 20B Mxfp4 Q8 with Q4 quantization. At approximately 80 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 | 80.00 tok/s | ✅ Fits comfortably |
| Q8 | 20GB | 24GB | 56.00 tok/s | ✅ Fits comfortably |
| FP16 | 40GB | 24GB | 30.40 tok/s | ❌ Not recommended |
RX 7900 XTX can run Mlx Community Gpt Oss 20B Mxfp4 Q8 at Q4 with an estimated 80 tok/s.
Q4 inference is estimated to need about 10GB VRAM on this page, while RX 7900 XTX has 24GB available.
If you need more speed or context headroom, compare alternative GPUs below and check higher-tier VRAM options.