Size Your Model to Where You Run It: Gemma 4 E2B and E4B on an AWS L4 and Two Small GPUs
Guidance on sizing Gemma models for AWS L4 or small GPUs using llama.cpp and CUDA.
Why this scored 18
every term, weightedEngagement gained per hour since the last capture, against the fastest item on its own source
Whether that velocity is itself speeding up, as a per-hour rate
How many independent communities are talking about the same entity
Decays to zero over 14 days
Subtracted once something is big and old — we rank what's next, not what's peaked
Weights are hand-tuned, not learned — we're calibrating them against realized trends as history accumulates. On a topic'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
Outlook
low confidence · estimate, not a guarantee7-day
~24
range 0–36
14-day
~26
range 0–40
30-day
~26
range 0–46
Signal history
7-day window (free)projected trajectory (estimate, not a guarantee)
Entities
Embed a live signal badge
[](https://www.signalcrest.app/topic/dev%3A4924519)
Drop this in a README or blog post — it updates automatically as the score moves.