community pool / model answer
Huihui-Qwen3.6-27B-abliterated-NVFP4-MTP
chat · sakamakismile/Huihui-Qwen3.6-27B-abliterated-NVFP4-MTP
97.5 tok/s · model median · 6 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| GB10 Grace Blackwell 128GB | 4-bit | 24 tok/s | reported | 348 | - GB | 262,144 | vllm |
| RTX 5090 32GB | 4-bit | 97.5 tok/s | measured | 115 | 32 GB | 131,072 | vllm |
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.