community pool / model answer
Qwen3.6-27B-Text-NVFP4-MTP
chat · sakamakismile/Qwen3.6-27B-Text-NVFP4-MTP
95.7 tok/s · model median · 6 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| RTX 5090 32GB | 4-bit | 121.9 tok/s | reported | 131 | 30 GB | 131,072 | vllm |
| RTX 5090 32GB ×2 | 4-bit | 85.3 tok/s | reported | 2,752 | 59.3 GB | 262,144 | vllm |
| RTX PRO 6000 Blackwell 96GB | 4-bit | 117.4 tok/s | reported | 75 | - GB | 262,144 | 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.