RX 7900 XT meets the minimum VRAM requirement for Q4 inference of Qwen/Qwen2.5-Coder-32B-Instruct. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.
RX 7900 XT can run Qwen/Qwen2.5-Coder-32B-Instruct with Q4 quantization. At approximately 43 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 | 17GB | 20GB | 43.26 tok/s | ✅ Fits comfortably |
| Q8 | 34GB | 20GB | 29.84 tok/s | ❌ Not recommended |
| FP16 | 67GB | 20GB | 17.42 tok/s | ❌ Not recommended |