Qwen 3.8 27B
Qwen family · 27.0B params
1recorded run
141.2best tok/s
1verified
Fastest GPUs for this model (best tok/s)
- RTX 4090141.2
All benchmarks Methodology
| GPU | Model | Quant | Backend | Ctx |
tok/s | prompt tok/s | VRAM GB | Source |
| RTX 4090 · 24 GB | Qwen 3.8 27B | int4 (output head only) | vllm pinned version (exact version not sp… | 38000 | 141.2 ✓ | — | — | src |