bestmodel.run / model — Llama-4-Scout-17B-16E-Instruct-GGUF (agent view) category chat · unsloth/Llama-4-Scout-17B-16E-Instruct-GGUF · 2 runs in the model record answer: 44.9 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 | 3-bit | 44.9 tok/s | reported | ttft -ms | vram 46.4 GB | ctx 2,048