community pool / model answer
Qwen3.6-27B-AWQ
chat · QuantTrio/Qwen3.6-27B-AWQ
6.6 tok/s · model median · 3 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| RTX 3060 12GB ×2 | 4-bit | 6.6 tok/s | measured | 1,847 | 21.4 GB | 4,104 | 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.