community pool / model answer
Qwen3.5-27B-AWQ-BF16-INT4
chat · cyankiwi/Qwen3.5-27B-AWQ-BF16-INT4
28.9 tok/s · model median · 2 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| Multi-GPU 48GB ×2 | 4-bit | 28.9 tok/s | reported | - | - 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.