AMD Instinct MI300X meets the minimum VRAM requirement for Q4 inference of FireRedTeam/FireRed-Image-Edit-1.0. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.
AMD Instinct MI300X can run FireRedTeam/FireRed-Image-Edit-1.0 with Q4 quantization. At approximately 769 tokens/second, you can expect Excellent speed - conversational response times under 1 second.
You have 188GB headroom, which is sufficient for system overhead and smooth operation.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 4GB | 192GB | 768.98 tok/s | ✅ Fits comfortably |
| Q8 | 8GB | 192GB | 513.95 tok/s | ✅ Fits comfortably |
| FP16 | 16GB | 192GB | 261.40 tok/s | ✅ Fits comfortably |