RTX 4070 Super meets the minimum VRAM requirement for Q4 inference of Qwen/Qwen-Image-Edit-2509. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.
RTX 4070 Super can run Qwen/Qwen-Image-Edit-2509 with Q4 quantization. At approximately 95 tokens/second, you can expect Good speed - acceptable for interactive use.
You have 8GB headroom, which is sufficient for system overhead and smooth operation.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 4GB | 12GB | 95.49 tok/s | ✅ Fits comfortably |
| Q8 | 8GB | 12GB | 65.00 tok/s | ✅ Fits comfortably |
| FP16 | 16GB | 12GB | 30.20 tok/s | ❌ Not recommended |