EmbeddingGemma 2Google
|
QVACTether Data
|
|||||
Related Products
|
||||||
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.
|
About
QVAC SDK is a developer toolkit for adding on-device AI inference to applications built with JavaScript/TypeScript or Python. It provides a common API for running supported language, vision, and speech models on mobile and desktop devices, with model discovery and downloads, inference APIs, and optional remote providers. Developers can build offline-capable AI features and, for local inference, keep prompts and processing on the device. QVAC also offers an OpenAI-compatible server and plugins that connect local models to developer tools. The SDK is intended for developers building AI-enabled applications. Its documentation covers setup, model selection, text generation, image and audio tasks, and tool calling; available features depend on the selected model and platform. QVAC SDK is free, open-source software under Apache 2.0; local inference requires no hosted QVAC account.
|
|||||
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
|
Platforms Supported
Windows
Supported
Mac
Supported
Linux
Supported
Cloud
Not Supported
On-Premises
Supported
iPhone
Supported
iPad
Supported
Android
Supported
Chromebook
Not Supported
|
|||||
Audience
Developers and AI teams wanting to build private, efficient, on-device multimodal search, retrieval, RAG, and semantic indexing systems
|
Audience
Software developers and product teams building AI-enabled mobile, desktop, and other applications that need local or peer-to-peer AI inference.
|
|||||
Support
Phone Support
Not Supported
24/7 Live Support
Not Supported
Online
Supported
|
Support
Phone Support
Not Supported
24/7 Live Support
Not Supported
Online
Supported
|
|||||
API
Offers API
Supported
|
API
Offers API
Supported
|
|||||
Screenshots and Videos |
Screenshots and VideosNo images available
|
|||||
Pricing
No information available.
Free Version
Not Supported
Free Trial
Not Supported
|
Pricing
$0
Free and open source under Apache 2.0. Local inference has no subscription, API-key, or per-token charge.
Free Version
Supported
Free Trial
Not Supported
|
|||||
Reviews/
|
Reviews/
|
|||||
Training
Documentation
Supported
Webinars
Not Supported
Live Online
Not Supported
In Person
Not Supported
|
Training
Documentation
Supported
Webinars
Not Supported
Live Online
Not Supported
In Person
Not Supported
|
|||||
Company InformationGoogle
Founded: 1998
United States
blog.google/innovation-and-ai/technology/developers-tools/embeddinggemma-2/
|
Company InformationTether Data
El Salvador
qvac.tether.io/products/sdk
|
|||||
Alternatives |
Alternatives |
|||||
|
|
|
|||||
|
|
|
|||||
|
|
|
|||||
|
|
||||||
Categories |
Categories |
|||||
Integrations
Hugging Face
Not Supported
OpenClaw
Not Supported
OpenCode
Not Supported
|
||||||
|
|
|