Signalcrest
← Back to feed
githubai

kimi-k3-in-c — A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, n

Large model on single CPU

Steady

12

signal score

🔗 2

sources · kimi k3

Cooling

7-day est. ~8

Why this scored 12

every term, weighted
Velocity+7.5 / 40 max

Engagement per hour, normalized against the fastest item on its own source

Acceleration+0.0 / 25 max

Whether that velocity is itself speeding up, as a per-hour rate

Cross-source spread+2.8 / 25 max

How many independent communities are talking about the same entity

Recency+7.3 / 10 max

Decays to zero over 14 days

Saturation penalty5.4 / 30 max

Subtracted once something is big and old — we rank what's next, not what's peaked

Composite12.1

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. Full methodology

Outlook

low confidence · estimate, not a guarantee

7-day

~8

range 78

14-day

~5

range 56

30-day

~4

range 35

Signal history

7-day window (free)

— — projected trajectory (estimate, not a guarantee)

Entities

kimi k3
Embed a live signal badge
Signalcrest signal badge
[![Signalcrest signal](https://www.signalcrest.app/api/badge/gh%3A1319154759)](https://www.signalcrest.app/topic/gh%3A1319154759)

Drop this in a README or blog post — it updates automatically as the score moves.