Qwen3.8-Flash-Next-W4A16-FP8PLE
1recorded run
186.9best tok/s
1verified
Fastest GPUs for this model (best tok/s)
- NVIDIA CMP 170HX x2186.9
| GPU | Model | Quant | Backend | Ctx | tok/s | prompt tok/s | VRAM GB | Source |
|---|---|---|---|---|---|---|---|---|
| NVIDIA CMP 170HX x2 · 64 GB | Qwen3.8-Flash-Next-W4A16-FP8PLE | W4A16-FP8PLE | vllm 0.29.0 | 262052 | 186.9 ✓ | — | — | src |