This page answers FireRedTeam/FireRed-Image-Edit-1.0 q8 quantization queries with explicit calculations from our model requirement dataset and compatibility speed table.
Exact Q8 requirement from model requirement data.
Throughput data below uses available compatibility measurements/estimates and is sorted by tokens per second for this model.
Need general guidance? Review full methodology.
| GPU | VRAM | Quantization | Speed | Compatibility |
|---|---|---|---|---|
| AMD Instinct MI300X | 192GB | Q8 | 514 tok/s | View full compatibility |
| NVIDIA H200 SXM 141GB | 141GB | Q8 | 467 tok/s | View full compatibility |
| AMD Instinct MI250X | 128GB | Q8 | 350 tok/s | View full compatibility |
| NVIDIA H100 SXM5 80GB | 80GB | Q8 | 313 tok/s | View full compatibility |
| NVIDIA H100 PCIe 80GB | 80GB | Q8 | 234 tok/s | View full compatibility |
| RTX 5090 | 32GB | Q8 | 231 tok/s | View full compatibility |
| NVIDIA A100 80GB SXM4 | 80GB | Q8 | 194 tok/s | View full compatibility |
| AMD Instinct MI210 | 64GB | Q8 | 150 tok/s | View full compatibility |
| NVIDIA A100 40GB PCIe | 40GB | Q8 | 149 tok/s | View full compatibility |
| NVIDIA A5000 | 24GB | Q4 | 136 tok/s | View full compatibility |
| NVIDIA L40 | 48GB | Q8 | 123 tok/s | View full compatibility |
| NVIDIA RTX 6000 Ada | 48GB | Q8 | 121 tok/s | View full compatibility |