EmbeddingGemma 300M

Google
Model overview

embeddinggemma-300m

Google's current public EmbeddingGemma 300M open-weight embedding model.

embeddingsearchraglocal inference
Representative version

embeddinggemma-300m

CompanyGoogle
ReleaseNot disclosed
Release typeModel release
Parameters0.3B
ArchitectureNot disclosed
ContextNot disclosed
Input modalitiestext
Output modalitiesvector
Tool use / function callingTool use: Not disclosed; Function calling: Not disclosed
Structured output / reasoningStructured output: Not disclosed; Reasoning: Not disclosed
Vision / audio / videoNot shown: Vision, Audio, Video
Open weights / LicenseWeights available / Gemma Terms of Use
License sourcegoogle-embeddinggemma-300m-current · 2026-08-04
Vendor APINot disclosed
API source pending verification
OpenRouterNot separately listed on OpenRouter
PricingNo reliable public source
BenchmarkNo reliable public source
Public signals1 community discussion / 1 activity snapshot
Use casessearch / rag / local inference / retrieval embeddings
Claim evidenceRelease event / Model specifications / Weight checkpointgoogle/embeddinggemma-300m · Hugging Faceembeddinggemma-300m · EmbeddingGemma 300M · embeddinggemma-300m
OpenRouter

Pricing / context / availability

OpenRouterNot separately listed on OpenRouter
OpenRouter listingNot separately listed in the current OpenRouter public list
Mapped versionembeddinggemma-300m
google-embeddinggemma-300m-current
PricingNo reliable public source
ContextNot disclosed
Speed/LatencyNo reliable public source
Snapshot time2026-08-11T06:28:09.895Z
SourceView source
Public activity counters

Hugging Face model-card activity snapshot

PlatformEntryLast-month downloadsCurrent likesCurrent SpacesTimeSource
huggingface
Current HF activity snapshot
google/embeddinggemma-300m2,109,9961,831100View source

Downloads are Hugging Face's trailing-month counter; likes and Spaces are snapshots at collection time.

Missing public information

Public information not yet available

Release date not disclosedNot listed on OpenRouterNo reliable benchmark sourceNo linkable model-specific reviewSpeed/latency not disclosed