DigUp for Designers

Download DigUp for Mac EmbeddingGemma 2 All roles

On-device flow Schematic: DigUp uses EmbeddingGemma 2 for Designers 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
Find a past moodboard photo	Index design libraries; describe the scene	Visual nearest neighbors in 768-d
Client markup PDF page	PDF page embeddings	Open at the marked page
Screen recording of a flow	Video moments + audio	Jump near the UI state
Export vs Figma naming chaos	Meaning search across folders	Keep Figma for edit; DigUp for find

Numbered checklist

Install DigUp; index Exports / References / Specs (local copies).
Allow first EmbeddingGemma 2 download (~865 MB).
Search visually (“dog on the beach”) or by UI text on Mac screenshots.
For huge photo libraries on CPU-only Win/Linux, expect slower photo indexing (README).
Link related: multimodal guide + vs Spotlight.

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.