community pool / model answer
Qwen3.6-27B-int4-AutoRound
chat · webhie/Qwen3.6-27B-int4-AutoRound
80.6 tok/s · model median · 10 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| Arc Pro B70 32GB | 4-bit | 66.4 tok/s | measured | 541 | - GB | 2,048 | vllm |
| Arc Pro B70 32GB ×2 | 4-bit | 89.4 tok/s | measured | 743 | - GB | 2,048 | 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.