google/embeddinggemma-2
google/embeddinggemma-2 is a feature extraction model published by google on Hugging Face. At the collection of October 24, 2026 it was No. 12 on the trending list, with 192,741 downloads in 30 days and 2,876 likes.
Collected · snapshot shipped with the site build, not a live feed
Why it is on the list
- No. 12 by Hugging Face trending score (281)
- +4 likes since 2026-10-23
- 192,741 downloads in the last 30 days
193K
2,876
Since October 23, 2026: +0 downloads (30-day figure), +4 likes
Positions and counts are Hugging Face’s; we report them and add no score of our own.
Source: Hugging Face public API · updated
Fact sheet
- Apache-2.0 · Commercial use allowedPermissive licence: commercial use is allowed, with the attribution and notice conditions of the licence.
- 744,371,512 parametersAbout 1.5 GB of weights at 16 bits; about 0.4 GB at a typical 4-bit quantisation.
- safetensors, transformers
- Open download
- ·
- 192,923
Most downloaded quantisations
- onnx-community/embeddinggemma-2-ONNX (opens in a new tab)
244K downloads in 30 days
- unsloth/embeddinggemma-2-GGUF (opens in a new tab)
122K downloads in 30 days
- ggml-org/embeddinggemma-2-GGUF (opens in a new tab)
85.1K downloads in 30 days
Questions about embeddinggemma-2
Why is google/embeddinggemma-2 trending?
No. 12 by Hugging Face trending score (281); +4 likes since 2026-10-23; 192,741 downloads in the last 30 days. Hugging Face does not publish the formula of its trending score; these are the public figures behind the position.
Can embeddinggemma-2 be used commercially?
The repository is tagged with the licence "Apache-2.0". Permissive licence: commercial use is allowed, with the attribution and notice conditions of the licence. The tag is set by the uploader, so confirm it against the licence file in the repository.
How large is embeddinggemma-2?
744M parameters according to the safetensors metadata. Weights alone take about 1.5 GB at 16 bits per parameter and about 0.4 GB in a typical 4-bit quantisation, before the memory needed for the context.
Are there quantised versions of embeddinggemma-2?
Yes. The most downloaded repositories that declare google/embeddinggemma-2 as their base are onnx-community/embeddinggemma-2-ONNX (244K downloads in 30 days), unsloth/embeddinggemma-2-GGUF (122K downloads in 30 days), ggml-org/embeddinggemma-2-GGUF (85.1K downloads in 30 days).