Marketplace · Embeddings

embeddinggemma:latest

Call embeddinggemma:latest through one OpenAI-compatible API. It's served by 2 hosts on the Inpherio grid, each at a price it sets — your request goes to the cheapest healthy one, and fails over to the next if it's down.

From
£0.0072
per 1M tokens
£1 buys about 140 million tokens (≈ 100 million words)
Hosts
2
Loaded now
0

At a glance.

  • Type: Embeddings
  • Hosts serving it now: 2 (0 with it loaded in memory)
  • Engines: ollama
  • Rentable: a whole host from £0.04 an hour (rentals)
python · openai sdk
from openai import OpenAI
client = OpenAI(base_url="https://inpherio.co.uk/v1",
                api_key=INPHERIO_API_KEY)
vec = client.embeddings.create(
    model="embeddinggemma:latest",
    input="text to embed",
)

embeddinggemma:latest in detail.

EmbeddingGemma is a 300M parameter embedding model from Google.

Published by
google
Parameters
303M
Download size
622 MB (as packaged for Ollama)
Quantisation
BF16
Format
gguf
Architecture
gemma3_text
Licence
Gemma terms · access is gated (accept the terms on Hugging Face)
Task
sentence similarity
Library
sentence-transformers
First published
17 Jul 2025
Last updated
25 Sep 2025
Downloads (30 days)
1.2 million on Hugging Face
Likes
2,103

sentence-transformers gemma3_text sentence-similarity feature-extraction text-embeddings-inference

The model card

Published by the model's authors on Ollama — shown as they wrote it, unedited by Inpherio.

This model requires Ollama v0.11.10 or later

EmbeddingGemma is a 300M parameter, state-of-the-art for its size, open embedding model from Google, built from Gemma 3 (with T5Gemma initialization) and the same research and technology used to create Gemini models. EmbeddingGemma produces vector representations of text, making it well-suited for search and retrieval tasks, including classification, clustering, and semantic similarity search. This model was trained with data in 100+ spoken languages.

The small size and on-device focus makes it possible to deploy in environments with limited resources such as mobile phones, laptops, or desktops, democratizing access to state of the art AI models and helping foster innovation for everyone.

Benchmark

Training Dataset

This model was trained on a dataset of text data that includes a wide variety of sources totaling approximately 320 billion tokens. Here are the key components:

• Web Documents: A diverse collection of web text ensures the model is exposed to a broad range of linguistic styles, topics, and vocabulary. The training dataset includes content in over 100 languages.

• Code and Technical Documents: Exposing the model to code and technical documentation helps it learn the structure and patterns of programming languages and specialized scientific content, which improves its understanding of code and technical questions.

• Synthetic and Task-Specific Data: Synthetically training data helps to teach the model specific skills. This includes curated data for tasks like information retrieval, classification, and sentiment analysis, which helps to fine-tune its performance for common embedding applications.

The combination of these diverse data sources is crucial for training a powerful multilingual embedding model that can handle a wide variety of different tasks and data formats.

Reference

Documentation

Sources: google/embeddinggemma-300m on Hugging Face · embeddinggemma:latest on Ollama. Collected from public sources on 8 Nov 2026; the host serving it may run a different build or quantisation — the marketplace shows each host's own measurements.

Who's serving it.

Every host benchmarked this model on its own hardware before serving it. Prices are set by each host; health is scored by the platform from what it observes.

Hosts serving embeddinggemma:latest right now
HostTierPriceMeasured speedHealthStateRent
Apple M4 (16 GIG )L1£0.0319 ms84loads on request—
7B-A1B (5G)L1£0.0072138 ms82loads on request£0.04/h

Live data, refreshed on every visit. How billing works.

Room on the grid for your machine.

2 machines serve embeddinggemma:latest today. Every extra host is somewhere a request can fail over to when one drops, and spare capacity when demand spikes. The router weighs price, measured speed, health and whether the model is already loaded — so a host with a sharper price or quicker hardware wins the next call.

Hosts now
2
0 loaded in memory
Price to beat
£0.0072
per 1M tokens
Fastest measured
19 ms

Set your own price — you keep 85% of what it earns, and new hosts start with 12 months fee-free (up to £250 of earnings). A payout fee of £2 + 1% per payout to a UK bank account, £2 + 2% to any other country applies when you're paid. Install the connector, load embeddinggemma:latest, and the platform benchmarks it on your hardware before your first request.