community pool / model answer

Qwen3.8-27B-NVFP4

chat · unsloth/Qwen3.8-27B-NVFP4

71.5 tok/s · model median · 9 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
GB10 Grace Blackwell 128GB4-bit11 tok/smeasured198- GB131,072sglang, vllm
GB10 Grace Blackwell 256GB4-bit17.4 tok/sreported168- GB2,048vllm
RTX 5090 32GB4-bit87.1 tok/smeasured13530 GB153,664vllm

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.