Marketplace · Embeddings
embeddinggemma-2:440m
Call embeddinggemma-2:440m through one OpenAI-compatible API. It's served by 1 host 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.
At a glance.
from openai import OpenAI
client = OpenAI(base_url="https://inpherio.co.uk/v1",
api_key=INPHERIO_API_KEY)
vec = client.embeddings.create(
model="embeddinggemma-2:440m",
input="text to embed",
)embeddinggemma-2:440m in detail.
EmbeddingGemma 2 is a multimodal embedding model from Google built on the Gemma 4 architecture.
- Published by
- Ollama library
- Parameters
- 271M
- Download size
- 671 MB (as packaged for Ollama)
- Quantisation
- Q8_0
- Format
- gguf
- Architecture
- gemma-embedding2
The model card
Published by the model's authors on Ollama — shown as they wrote it, unedited by Inpherio.
EmbeddingGemma 2 is an open multimodal embedding model built by Google DeepMind which maps text (incl. code), images, video, and audio inputs—and combinations thereof—into a single, unified 768-dimensional vector space. The model has 740M total parameters, combining a 270M parameter text model with modular vision (170M) and audio (300M) encoders.
Designed to run on consumer hardware such as mobile devices and laptops, EmbeddingGemma 2 delivers low-latency semantic representations for on-device applications, like search, retrieval-augmented generation (RAG), classification, and clustering.
EmbeddingGemma 2 builds upon the architectural and capability advancements of Gemma 4, offering several core features:
• Native multimodality: Native multimodality: Unifies 4 modalities (text, images, video, and audio) in a single shared 768-dimensional embedding space.
• Multilinguality and code: EmbeddingGemma 2 understands 100+ languages, and achieves a ~14% improvement on code tasks relative to its predecessor.
• Flexible footprint: Combines a 270M parameter text backbone (130M transformer + 140M embedder) with selectively loadable vision (170M) and audio (300M) encoders, allowing developers to load only the modalities required for their use case.
• Matryoshka Representation Learning (MRL): Native support for truncated embeddings across 128d, 256d, 512d, and 768d, enabling up to a 6x reduction in vector storage costs with minimal impact on quality.
• Context length: 8K token context window, capable of processing minutes of audio or video.
• Task-steered representations: Uses lightweight text instruction prefixes to optimize embeddings for different tasks (search, classification, clustering, semantic similarity, etc.).
Model Overview
Parameters Total 740M
Backbone 130M
Embedder 140M
Modality Encoders Vision: 170M Audio: 300M
Architecture Layers 24
Model Dimension 512
Hidden Dimension 2048
Sliding Window 1024 tokens
Vocabulary Size 262,144
Heads
4
KV-Heads (Local/Global)
2⁄1
Local:Global 5:1
Attention GQA/MQA
Activation Gated FFN with GELU
Pooling Mean Pooling
Projection Layer 512→768
Input/Output Supported Modalities Text, Images, Video, Audio
Context Window 8,192 tokens
Native Output Dimension 768
MRL Truncation Dimensions 128, 256, 512
Benchmark Results
EmbeddingGemma 2 was evaluated across text, code, vision, visual document, video, and audio embedding benchmarks. All results reported below use the full-precision checkpoint.
Overall Evaluation Results (768d)
Modality Benchmark Metric EmbeddingGemma 2 EmbeddingGemma 1
Text Massive Text Embedding Benchmark (MTEB, multilingual, v2) Mean(Task), Multiple 61.36 61.15
Massive Text Embedding Benchmark (MTEB, code, v1) Mean(Task), NDCG@10 78.68 68.76
Image Massive Image Embedding Benchmark (MIEB, lite) Mean(TaskType), Multiple 65.67 -
Massive Multimodal Embedding Benchmark (MMEB v2 - Image) Mean(Task), Hit@1 57.28 -
Massive Multimodal Embedding Benchmark (MMEB v2 - VisDoc) Mean(Task), NDCG@5 67.84 -
Video Massive Multimodal Embedding Benchmark (MMEB v2 - Video) Mean(Task), Hit@1 50.67 -
Audio Massive Sound Embedding Benchmark (MSEB, Retrieval) Mean(Task), MRR@10 69.54 -
Massive Audio Embedding Benchmark (MAEB) Hugging Face Mean(Task), Multiple 49.87 -
Evaluation Results with Vector Truncation
With MRL, EmbeddingGemma 2 representations can be truncated below the native 768d to 128d, 256d, and 512d representations and re-normalized. With this, model users can reduce storage requirements, with minimal quality impact down to 256d. 128d is best suited to text-only workloads.
Output Dimension Compression Ratio MTEB (multilingual, v2) Mean(Task) MTEB (eng, v2) Mean(Task) MTEB (code, v1) Mean(Task) MIEB (lite) Mean(TaskType) MMEB (v2) Overall MSEB (Retrieval) Mean(Task) MAEB Mean(Task)
768d (Full) 1:1 61.36 68.46 78.68 65.67 59.01 69.54 49.87
512d 1:1.5 61.17 68.41 77.24 65.34 58.38 69.18 49.76
256d 1:3 60.41 67.78 76.18 64.16 56.24 66.76 49.13
128d 1:6 57.89 65.68 71.41 59.97 45.65 56.71 47.28
Sources: embeddinggemma-2:440m on Ollama. Collected from public sources on 15 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.
| Host | Tier | Price | Measured speed | Health | State | Rent |
|---|---|---|---|---|---|---|
| GTX 1080 Ti (11G) | L1 | £0.0072 | 35 ms | 78 | loads on request | £0.60/h |
Live data, refreshed on every visit. How billing works.
Room on the grid for your machine.
Right now one machine serves embeddinggemma-2:440m. If it drops, so does every request for it — a second host is what turns it into failover, and the grid needs that more than another copy. 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.
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-2:440m, and the platform benchmarks it on your hardware before your first request.