community pool / model answer
Qwen3.6-27B-AWQ-BF16-INT4-mtp-bf16
chat · hampsonw/Qwen3.6-27B-AWQ-BF16-INT4-mtp-bf16
57.5 tok/s · model median · 2 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| RTX 3090 24GB ×2 | 4-bit | 57.5 tok/s | reported | - | - GB | 16,384 | 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.