orcarouter
for AI engineers, ML developers
Why this scored 0
every term, weightedIts fastest-moving item, measured against the pace of its own source
Whether that velocity is itself speeding up, as a per-hour rate
How many independent communities its own items come from
Decays to zero over 14 days, counted from when we first saw it
Subtracted once something is big and old — sized by its biggest item, aged from when we first saw it
Weights are hand-tuned, not learned — we're calibrating them against realized trends as history accumulates. On an entity's first sighting there's no previous reading to compare against, so acceleration starts from a neutral prior rather than a measurement, and velocity falls back to engagement over its whole lifetime until a second reading exists. Full methodology
Signal history
7-day window (free)The evidence
The live items this entity's score aggregates — every community independently talking about it right now. This is the corroboration, shown, not claimed.
- 120
orcarouter/GLM-5.3-Flash-Uncensored-FP8 (text-generation)
GLM-5.3 flash model with FP8 precision enables faster uncensored text generation. · for ml researchers, llm developers
huggingfaceSteady 2 · glm5.3ai−8 saturated41d ago - 20
orcarouter/Qwen3.8-27B-Uncensored-GGUF (image-text-to-text)
Publishes uncensored Qwen 3.8B model in GGUF format for local inference. · for AI engineers, ML developers
huggingfaceSteadyai−18 saturated53d ago - 30
orcarouter/Qwen3.8-27B-Uncensored (image-text-to-text)
The open-source Qwen 3.8B uncensored model adds image-to-text capability for multimodal projects. · for ml researchers, ai startup founders
huggingfaceSteadyai−14 saturated48d ago