DigUp for Researchers — Papers, Lab Notes & Experiment Media

Download DigUp for Mac EmbeddingGemma 2 All roles

On-device flow Schematic: DigUp uses EmbeddingGemma 2 for Researchers and scientists local search

Original schematic — DigUp indexes local files with EmbeddingGemma 2 (llama.cpp).

Sourced snapshot (2026-10-15)

Fact	Value	Source
Model	EmbeddingGemma 2 · ~740M params · ~865 MB Q8 via llama.cpp	Google AI · DigUp README
Vector space	768-d shared multimodal space	Google AI · DigUp README
Mac / Win·Linux	0.6.1 · 0.7.0-beta.1	GitHub Releases
Stars / forks	~3,768 / ~254	GitHub API

Pain → DigUp workflow → tip

Pain	DigUp + EmbeddingGemma 2 workflow	Tip
Which PDF has that plot?	PDF + image embeddings	Open page / find figure shot
Notebook cell explaining preprocess	Opt-in code: search	Jupyter without outputs (README)
Microscope video moment	Video frames	Jump near event
Reproducibility offline	Local index	~865 MB model once; then offline search

Numbered checklist

Install DigUp on your lab machine (Apple Silicon or Win/Linux beta).
Index Papers / LabNotes / Captures — ensure files are local.
Enable code search for analysis repos.
Combine semantic queries with exact citation keys.
Read EmbeddingGemma docs + DigUp model page for 740M / 768-d facts.

Why EmbeddingGemma 2 matters here

Google’s EmbeddingGemma 2 (~740M, unified 768-d multimodal space) is what DigUp runs via llama.cpp (~865 MB Q8 package). One query can rank images, PDF pages, audio windows, video frames, and optional code — see the local multimodal guide and model page. digup.run is not Google-official.