EmbeddingGemma 2Google
|
d1.2Liquid AI
|
|||||
| EmbeddingGemma 2 | d1.2 | |||||
|---|---|---|---|---|---|---|
Related Products
|
||||||
EmbeddingGemma 2:
About
EmbeddingGemma 2 is an open, lightweight multimodal embedding model designed to map text, code, images, video, and audio into a shared embedding space for search, retrieval, classification, routing, and RAG applications. Built on the Gemma 4 architecture and released under the Apache 2.0 license, it has 740 million parameters and is optimized for on-device inference. Its modular design can use as little as 270M parameters for text-only workloads, with optional vision and audio encoders for full multimodal support. Matryoshka Representation Learning lets developers reduce output vectors from 768 dimensions to 512, 256, or 128, lowering storage and memory requirements for local vector databases. The model supports an 8K-token context window and can process up to 5.5 minutes of audio, 29 images, 58 video frames, or interleaved combinations on local hardware.
|
d1.2:
About
d1.2 is Liquid AI’s hosted decision-model service, available through the Liquid API in d1.2 and d1.2-ultra variants. It is designed for classification, routing, scoring, and extracting structured answers from text, images, and audio. Developers can submit a state and one or more questions, then receive typed results such as text, numbers, dates, spans, bounding boxes, multiple-choice selections, and associated probabilities. Document workflows can use it to read invoice fields, identify passages such as personal data, or locate items in images; audio inputs can support classification tasks such as detecting sounds or identifying spoken language. The API uses an endpoint and key-based authentication, allowing application teams to add these decision-model capabilities to their own workflows.
|
|||||
EmbeddingGemma 2:
Platforms Supported
Windows
Not Supported
Mac
Not Supported
Linux
Not Supported
Cloud
Supported
On-Premises
Not Supported
iPhone
Not Supported
iPad
Not Supported
Android
Not Supported
Chromebook
Not Supported
|
d1.2:
Platforms Supported
Windows
Not Supported
Mac
Not Supported
Linux
Not Supported
Cloud
Supported
On-Premises
Not Supported
iPhone
Not Supported
iPad
Not Supported
Android
Not Supported
Chromebook
Not Supported
|
|||||
EmbeddingGemma 2:
Audience
Developers and AI teams wanting to build private, efficient, on-device multimodal search, retrieval, RAG, and semantic indexing systems
|
d1.2:
Audience
Developers and product or engineering teams adding classification, routing, scoring, or structured extraction from text, images, and audio to applications and workflows.
|
|||||
EmbeddingGemma 2:
Support
Phone Support
Not Supported
24/7 Live Support
Not Supported
Online
Supported
|
d1.2:
Support
Phone Support
Not Supported
24/7 Live Support
Not Supported
Online
Not Supported
|
|||||
EmbeddingGemma 2:
API
Offers API
Supported
|
d1.2:
API
Offers API
Supported
|
|||||
EmbeddingGemma 2:
Screenshots and Videos |
d1.2:
Screenshots and Videos |
|||||
EmbeddingGemma 2:
Pricing
No information available.
Free Version
Not Supported
Free Trial
Not Supported
|
d1.2:
Pricing
$0.02 per 1M tokens (input)
Free Version
Not Supported
Free Trial
Not Supported
|
|||||
EmbeddingGemma 2:
Reviews/
|
d1.2:
Reviews/
|
|||||
EmbeddingGemma 2:
Training
Documentation
Supported
Webinars
Not Supported
Live Online
Not Supported
In Person
Not Supported
|
d1.2:
Training
Documentation
Supported
Webinars
Not Supported
Live Online
Not Supported
In Person
Not Supported
|
|||||
EmbeddingGemma 2:
Company InformationGoogle
Founded: 1998
United States
blog.google/innovation-and-ai/technology/developers-tools/embeddinggemma-2/
|
d1.2:
Company InformationLiquid AI
Founded: 2023
United States
www.liquid.ai
|
|||||
EmbeddingGemma 2:
Alternatives |
d1.2:
Alternatives |
|||||
|
EmbeddingGemma 2:
|
d1.2:
|
|||||
|
EmbeddingGemma 2:
|
d1.2:
|
|||||
|
EmbeddingGemma 2:
|
d1.2:
|
|||||
|
EmbeddingGemma 2:
|
d1.2:
|
|||||
EmbeddingGemma 2:
Categories |
d1.2:
Categories |
|||||
EmbeddingGemma 2:
Integrations
No info available.
|
d1.2:
Integrations
No info available.
|
|||||
|
EmbeddingGemma 2:
|
d1.2:
|