community pool / model answer

Qwen3.6-27B-PrismaSCOUT-Blackwell-NVFP4-BF16-vllm

chat · rdtand/Qwen3.6-27B-PrismaSCOUT-Blackwell-NVFP4-BF16-vllm

18.9 tok/s · model median · 1 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
GB10 Grace Blackwell 128GB4-bit18.9 tok/sreported-- GB2,048vllm

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.