Github Trends®
8676 findingsmedian surprise 0.00441window 3 days
UNIT / TREND-MONITOR · REV 2.6
[ 3 days window ]
SOURCE: own snapshots
FINDING #383 · UNIT ID 1308124634
FedericoTs/quantprobe
Run a 110B on a 2016 PC with 16 GB RAM. Know your tok/s before you download. Placement beats budget: predicts speed + memory fit for any GGUF on your exact hardware, self-calibrates, emits the exact llama.cpp command — or 'quantprobe auto' does it all. Falsification-tested laws; misses published at full size. pip install quantprobe
[ PYTHON ][ GITHUB ↗ ]
SURPRISE SCORE
0.00

Score Breakdown

SURPRISE0.11
ENGAGEMENT0.29
FRESHNESS1.00
SCORE = SURPRISE × ENGAGEMENT^0.7 × FRESHNESS × VISIBILITY × CONFIDENCE
SURPRISE = WINDOW STARS / DAYS / (AUDIENCE + FLOOR)
22% OF STARS IN ARCHIVE

Growth Telemetry

VELOCITY /D
6.00
ACCEL
-7.00
RETENTION
10.0%
PEAK 2026-08-08 · FORK-RETENTION 0.0% · 18 STARS / WINDOW

Author Audience

AUDIENCE
13
FOLLOWERS
5
OWNER ★
81

Engagement Signals

FORKS
7
ISSUE AUTH
0
PR AUTH
0
UNIQUE STARGAZERS 18 / 18 (DIVERSITY 1.00)

Why This Is A Finding

FedericoTs/quantprobe собрал 18 звёзд за окно, тогда как у автора всего 5 подписчиков — эффективная аудитория ≈ 13. Это даёт surprise-индекс 0.11 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 0.0% и 0 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация отрицательная — внимание остывает после пика.

METRICS IN CONTEXT

MEDIAN ACROSS ALL 8676 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW
METRICVALUEMEDIANΔ MEDPERCENTILE
SCORE0.040.00+0.04ABOVE 96%
VELOCITY6.005.67+0.33ABOVE 51%
RETENTION10.0%33.3%-23.3 PPABOVE 41%
FORKS7339-332ABOVE 5%
SURPRISE0.110.00+0.11ABOVE 95%