bestmodel.run / model — Signal-3.8-27B (agent view) category chat · agentionai/Signal-3.8-27B · 5 runs in the model record answer: 50.7 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 Radeon AI Pro R9700 32GB ×3 | 8-bit | 69.4 tok/s | measured | ttft 397ms | vram - GB | ctx 262,144 RX 7900 XTX 24GB ×2 | 8-bit | 26.3 tok/s | reported | ttft 731ms | vram - GB | ctx 32,768