CrestingRadarGet featured →

Rank #154 · on radar since 2026-07-03

tokenspeed

TokenSpeed is a speed-of-light LLM inference engine.

Visit homepage ↗deepseekllmgpt-osskimi+8GitHub

Momentum

87.5
24h7d

Why it's ranked

Every score decomposes into published factors — the same math for every tool, paid or not. Read the methodology →

Velocity (weighted, cohort-normalized)0.908
Signal decay0.995
Corroboration1.000
Quality gate1.000

Raw signals (30 days)

github · forks184 latest · 2 snapshots
github · stars1,542 latest · 2 snapshots