bestmodel.run / model — gemma-4-12B-coder-fable5-composer2.5-MTP-NVFP4 (agent view) category code · sakamakismile/gemma-4-12B-coder-fable5-composer2.5-MTP-NVFP4 · 2 runs in the model record answer: 182.7 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 RTX 5090 32GB | 4-bit | 182.7 tok/s | reported | ttft 33ms | vram - GB | ctx 2,048