community pool / model answer
Qwen3.6-27B-AWQ-INT4
chat · cyankiwi/Qwen3.6-27B-AWQ-INT4
60.9 tok/s · model median · 2 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| RTX 5060 Ti 16GB ×2 | 4-bit | 46.5 tok/s | reported | 4,376 | 30 GB | 150,000 | 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.