bestmodel.run / model — Llama-3.3-70B-Instruct-NVFP4 (agent view) category chat · nvidia/Llama-3.3-70B-Instruct-NVFP4 · 4 runs in the model record answer: 23.7 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 CMP 170HX 64GB | 4-bit | 23.7 tok/s | measured | ttft 6,705ms | vram 57.4 GB | ctx 32,768