embeddinggemma-300m
- Task
- Sentence similarity
- Category
- Embeddings
- License
- Gemma license
- Commercial use
- Yes, with conditions
The publisher's own model license: commercial use is allowed under its terms, which include limits; read them before shipping. - Size
- About 300 million parameters
- Memory to load
- ~1 GB (estimate)
- Format
- TFLITE
- Runs on
- CPU
- Access
- Gated: accept the publisher's terms on Hugging Face
- Downloads (last 30 days)
- 125K
- Likes
- 100
- Last updated
- October 7, 2026
How to run it
This is a TensorFlow Lite build for phones and edge devices.
Plan for roughly 1 GB of memory to load it (our estimate from its size and format).
Downloads are gated: accept the publisher's terms on Hugging Face first.
The model card on Hugging Face has the exact usage code.
Where to run it
In the cloud
Needs about 1 GB: a 24 GB GPU such as an RTX 4090 or RTX A5000 is enough.
- RunPod · rent a GPU by the hour (affiliate link)
Related sentence similarity models
Data from Hugging Face's public API, last checked November 8, 2026. Downloads are Hugging Face's count for the last 30 days.