RX 7900 GRE meets the minimum VRAM requirement for Q4 inference of Qwen/Qwen2.5-7B-Instruct. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.
RX 7900 GRE can run Qwen/Qwen2.5-7B-Instruct with Q4 quantization. At approximately 93 tokens/second, you can expect Good speed - acceptable for interactive use.
You have 12GB headroom, which is sufficient for system overhead and smooth operation.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 4GB | 16GB | 92.72 tok/s | ✅ Fits comfortably |
| Q8 | 8GB | 16GB | 63.83 tok/s | ✅ Fits comfortably |
| FP16 | 16GB | 16GB | 35.01 tok/s | ⚠️ Tight fit |