AMD Radeon Pro W7800 meets the minimum VRAM requirement for Q4 inference of deepseek-ai/DeepSeek-R1. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.
AMD Radeon Pro W7800 can run deepseek-ai/DeepSeek-R1 with Q4 quantization. At approximately 94 tokens/second, you can expect Good speed - acceptable for interactive use.
You have 28GB headroom, which is sufficient for system overhead and smooth operation.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 4GB | 32GB | 93.80 tok/s | ✅ Fits comfortably |
| Q8 | 7GB | 32GB | 66.52 tok/s | ✅ Fits comfortably |
| FP16 | 15GB | 32GB | 32.41 tok/s | ✅ Fits comfortably |