bestmodel.run / model — Qwen3.8-Flash-Next-NVFP4 (agent view) category chat · nvidia/Qwen3.8-Flash-Next-NVFP4 · 3 runs in the model record answer: 112.8 tok/s (model median) Honesty ladder: measured > reported > extrapolated > formula > no data yet. Empty fields stay empty — never filled with an estimate. rig | quant | median result | basis | ttft | peak vram | max context GB10 Grace Blackwell 256GB | 4-bit | 62.9 tok/s | reported | ttft 332ms | vram - GB | ctx 262,144 RTX PRO 6000 Blackwell 96GB ×2 | 4-bit | 83.8 tok/s | reported | ttft 166ms | vram - GB | ctx 2,048 RTX PRO 6000 Blackwell Workstation Edition 96GB ×2 | 4-bit | 260.1 tok/s | reported | ttft 450ms | vram 179.1 GB | ctx 262,144