community pool / model answer

Qwen3.8-Flash-Next-NVFP4

chat · local-inference-lab/Qwen3.8-Flash-Next-NVFP4

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

Answer

93.5tok/s

reportedRTX PRO 6000 Blackwell 96GB ×24-bit · 1 run · decodebest cell in the pool

  1. RTX PRO 6000 Blackwell 96GB ×293.5 tok/sreported1 run · peak VRAM no data yet · 192 GB rig memory
Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX PRO 6000 Blackwell 96GB ×24-bit93.5 tok/sreported171- 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.