bestmodel.run / model — DeepSeek-V4.1-Flash-UNCENSORED-FP8 (agent view) category chat · dealignai/DeepSeek-V4.1-Flash-UNCENSORED-FP8 · 1 runs in the model record answer: 316.6 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 RTX PRO 6000 Blackwell Max-Q Workstation Edition 96GB ×4 | 8-bit | 316.6 tok/s | reported | ttft 289ms | vram - GB | ctx 524,288