community pool / model answer
Qwen3.8-27B-NVFP4
chat · RadixArk/Qwen3.8-27B-NVFP4
35.3 tok/s · model median · 4 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| GB10 Grace Blackwell 128GB | 4-bit | 23.6 tok/s | measured | 226 | - GB | 131,072 | sglang, vllm |
| RTX PRO 6000 Blackwell 96GB | 4-bit | 97.4 tok/s | reported | 40 | - GB | 2,048 | sglang |
Context tested
The table above is the tested context for each exact rig and quantization cell. Empty fields remain empty rather than being filled with an estimate.