AMD Radeon Pro W7900 meets the minimum VRAM requirement for Q4 inference of Qwen/Qwen2.5-32B. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.
AMD Radeon Pro W7900 can run Qwen/Qwen2.5-32B with Q4 quantization. At approximately 52 tokens/second, you can expect Good speed - acceptable for interactive use.
You have 32GB headroom, which is sufficient for system overhead and smooth operation.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 16GB | 48GB | 52.44 tok/s | ✅ Fits comfortably |
| Q8 | 33GB | 48GB | 38.24 tok/s | ✅ Fits comfortably |
| FP16 | 66GB | 48GB | 19.55 tok/s | ❌ Not recommended |