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 rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 3090 24GB ×24-bit43.2 tok/sreported1,989- GB2,048vllm
RTX 3090 24GB ×44-bit67.1 tok/sreported57592.5 GB262,144vllm
RTX A6000 48GB ×24-bit147.4 tok/sreported12982.4 GB262,144vllm

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.