SOURCE-REVIEWED MODEL PROFILE
embeddinggemma-300m
A compact multilingual embedding model for semantic retrieval and similarity, rather than answer generation.
Metadata reviewed 2026-10-24 · Original creator: Google
What it does
- Vector representations
- External task-specific runtime; not integrated into launcher chat
Local fit
Very small model / edge candidate; runtime validation required. Embedding output is a vector. This launcher’s chat and project memory do not automatically use it.
Runtime limits and on-device memory must be validated separately.
Evidence and limits
Source reviewed only. No local model or Android inference test performed.
External task-specific runtime; not integrated into launcher chat
License and source
Gemma terms apply; review and accept access conditions yourself. No weights or license acceptance are bundled.
Read the original model card ↗
Reviewed source revision: 57c266a740f537b4dc058e1b0cda161fd15afa75