DeepSeek's MoE model with 552B total parameters and 8-16B active per token. 1M-token context, MIT license: free commercial use. Built for online serving, too large for local use on a single PC.
Back to resources
Models🎯
EmbeddingGemma 2
Released on Oct 28, 2026
740M-parameter multimodal embedding model (270M text, 170M vision, 300M audio, selectively loadable): text, code, images, video and audio in a unified 768-dimension space, 100+ languages, 8K context, Matryoshka vectors (128/256/512/768) that cut storage by up to 6x. Apache 2.0, runs on phones and laptops.
Features
- 740M parameters
- 4 modalities
- 768-d space
- Matryoshka up to 6x
- Apache 2.0
Tags
Useful links
Discover EmbeddingGemma 2
Visit the official site to download, learn more and start using EmbeddingGemma 2.
Related resources — Models
Models⚡
DeepSeek V4.1 Flash
Released Sep 10, 2026DeepSeek V4.1 Flash
LLMDeepSeekMoEOpen Source
Models⚡
FLUX.1 [dev]
Released Aug 1, 2024FLUX.2 [klein] 4B/9B
The most advanced open image model: excellent prompt adherence, solid anatomy, full fine-tuning. The standard for serious work.
ImmaginiDiffusionFLUX
Models⚡
FLUX.1 [schnell]
Released Aug 1, 2024FLUX.2 [klein] 4B/9B
Very few steps, high quality, and strong text rendering. The distilled FLUX variant, built for speed.
ImmaginiDiffusionFLUX

