Huihui-Qwen3.8-27B-abliterated
Qwen family · 28.0B params
1recorded run
117.7best tok/s
1verified
Fastest GPUs for this model (best tok/s)
- RTX 5090117.7
All benchmarks Methodology
| GPU | Model | Quant | Backend | Ctx |
tok/s | prompt tok/s | VRAM GB | Source |
| RTX 5090 · 32 GB | Huihui-Qwen3.8-27B-abliterated | NVFP4 | vllm 0.27.2rc1.dev122+g8efa13b70 | 172800 | 117.7 ✓ | 7466.2 | — | src |