community pool / model answer

Qwen3.6-27B-FP8

chat · vrfai/Qwen3.6-27B-FP8

41.5 tok/s · model median · 11 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
Arc Pro B70 32GB ×48-bit41.5 tok/smeasured-- GB32,768vllm

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.