community pool / model answer
Qwen3.6-27B-AWQ-BF16-INT4
chat · cyankiwi/Qwen3.6-27B-AWQ-BF16-INT4
98.1 tok/s · model median · 5 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| RTX 3090 24GB ×2 | 4-bit | 43.2 tok/s | reported | 1,989 | - GB | 2,048 | vllm |
| RTX 3090 24GB ×4 | 4-bit | 67.1 tok/s | reported | 575 | 92.5 GB | 262,144 | vllm |
| RTX A6000 48GB ×2 | 4-bit | 147.4 tok/s | reported | 129 | 82.4 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.