Models
| Model ID | Total Weight | Hosts | Inferences | AI Tokens |
|---|---|---|---|---|
| Qwen/Qwen3-235B-A22B-Instruct-2507-FP8 | 1,852,302 | 314 | 564 | 1,088,226 |
| Qwen/Qwen3-32B-FP8 | 495,906 | 110 | 257 | 125,707 |
| Qwen/QwQ-32B | 62,831 | 20 | 10 | 13,376 |
| Qwen/Qwen2.5-7B-Instruct | 58,655 | 30 | 425 | 339,790 |
| RedHatAI/Qwen2.5-7B-Instruct-quantized.w8a16 | 0 | 0 | - | - |