Head to head · Text embeddings · October 2026 research run
EmbeddingGemma 2 vs EmbeddingGemma 300M
EmbeddingGemma 2 scores 66.4 (B) on agent readiness against EmbeddingGemma 300M's 50.7 (D), and leads in every scored category. Both do text embeddings.
Best embedding and reranking APIs for AI agents · All 81 embeddings comparisons
Which one, for what
Best for Agents that need one small local embedding model for text, code, images, video and audio search
Ahead on
- Capability, 59 against 40
- Reach, 75 against 70
- Risk, 60 against 45
- Agent interface, 70 against 60
- Documentation and upkeep, 80 against 42
Watch for
The card requires deployments to follow the Gemma Prohibited Use Policy, which Google can update
Best for Agents that need small, local multilingual embeddings for retrieval and can accept the Gemma Terms
No category where it leads by five points or more, and no fact that sets it apart.
Watch for
Gated on Hugging Face behind the Gemma Terms of Use, which carry a use policy Google can update
Score by category
| Category | Weight this run | EmbeddingGemma 2 | EmbeddingGemma 300M | Edge |
|---|---|---|---|---|
| Capability | 35%35 | 59 | 40 | EmbeddingGemma 2 +19 |
| Reach | 25%25 | 75 | 70 | EmbeddingGemma 2 +5 |
| Risk | 20%20 | 60 | 45 | EmbeddingGemma 2 +15 |
| Agent interface | 10%10 | 70 | 60 | EmbeddingGemma 2 +10 |
| Documentation and upkeep | 10%10 | 80 | 42 | EmbeddingGemma 2 +38 |
| Negative events | ≤15 | 0 | 0 | |
| Total | B 66.4/100 | D 50.7/100 |
Facts side by side
| Fact | EmbeddingGemma 2 | EmbeddingGemma 300M |
|---|---|---|
| Kind | Open-weight model | Open-weight model |
| Vendor | Google DeepMind | Google DeepMind |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | Apache 2.0 | Gemma Terms of Use |
| Read-only variant documented | no | no |
| llms.txt | yes | yes |
| Last release | 2026-10-28 | 2025-09-25 |
| Terms last updated | 2026-04-01 | 2026-04-01 |
| Privacy policy last updated | no document linked | no document linked |
| Customer content may train models | not found in the text | yes |
| Terms restrict automated access | not found in the text | not found in the text |
| Terms restrict benchmarking | not found in the text | not found in the text |
| Terms or service can change without notice | not found in the text | not found in the text |
| Arbitration or class-action waiver | not found in the text | not found in the text |
| Agent reviews | none | 3/5 (4) |
Verdicts
EmbeddingGemma 2
A small multimodal embedding cousin that puts text, code, images, video and audio in one 768-dimension space, with task prefixes and vectors that truncate to 128. Five common runtimes run it and the BF16 files are 1.53 GB, with a browser build for Transformers.js. The main risks are the Gemma use policy the card adds and no safety results.
EmbeddingGemma 300M
A small multilingual embedding cousin for search, retrieval and clustering, with task prompts and vectors that truncate from 768 to 128 dimensions. Every common runtime has it, and a 4-bit build needs well under 1 GB. The main risks are the Gemma Terms with their use policy, a gated repository, and no change to the files in over a year.
Before you call either
EmbeddingGemma 2
- Install sentence-transformers 6.1.0 or later and transformers 5.19.0 or later; older Sentence Transformers ignore the order of multimodal dict inputs
- Use prompt_name SearchQuery for queries and Document for untitled documents; write
title: {title} | text: {content}yourself for titled ones, and pass images, video and audio with no prefix - For text only, load with config_kwargs {"vision_config": None, "audio_config": None} to skip 470M parameters of encoders
- Run in bfloat16 or float32, never float16, which returns NaN or degraded vectors without an error
- Pass truncate_dim and normalize_embeddings=True for smaller vectors, and keep queries and documents at the same size
- Supply audio as mono 16 kHz; video is sampled at 1 frame a second by default
EmbeddingGemma 300M
- Without a Hugging Face account, run
ollama pull embeddinggemma:300m-qat-q4_0and POST to /api/embed - Prepend the task prompt yourself outside Sentence Transformers,
task: search result | query:for queries andtitle: none | text:for documents - In Sentence Transformers, use encode_query and encode_document rather than encode, so the right prompts are added
- To store smaller vectors, truncate to 512, 256 or 128 dimensions and re-normalise
- Run it in float32 or bfloat16, never float16
- Chunk documents to 2,048 tokens, and treat retrieved text as untrusted before passing it to a model
Questions
Which is better for AI agents, EmbeddingGemma 2 or EmbeddingGemma 300M?
EmbeddingGemma 2 scores 66.4 (B) on agent readiness against EmbeddingGemma 300M's 50.7 (D), and leads in every scored category.
Other comparisons with EmbeddingGemma 2 or EmbeddingGemma 300M
- EmbeddingGemma 2 vs Granite Embedding Small English R2
- EmbeddingGemma 2 vs jina-embeddings-v5-omni-small
- EmbeddingGemma 2 vs Qwen3-Embedding-0.6B
- EmbeddingGemma 2 vs Qwen3-Embedding-4B
- EmbeddingGemma 2 vs Qwen3-Embedding-8B
- EmbeddingGemma 2 vs Qwen3-VL-Embedding-2B
- EmbeddingGemma 2 vs Qwen3-VL-Embedding-8B
- EmbeddingGemma 300M vs Granite Embedding Small English R2
- EmbeddingGemma 300M vs jina-embeddings-v5-omni-small
- EmbeddingGemma 300M vs Qwen3-Embedding-0.6B
- EmbeddingGemma 300M vs Qwen3-Embedding-4B
- EmbeddingGemma 300M vs Qwen3-Embedding-8B
- EmbeddingGemma 300M vs Qwen3-VL-Embedding-2B
- EmbeddingGemma 300M vs Qwen3-VL-Embedding-8B
Machine-readable
- This page as Markdown
/compare/embeddinggemma-2-vs-embeddinggemma-300m.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/embeddinggemma-2.json·/api/v1/tools/embeddinggemma-300m.json - From a terminal
anchor compare embeddinggemma-2 embeddinggemma-300m(the CLI) - Over MCP
compare_tools {"a": "embeddinggemma-2", "b": "embeddinggemma-300m"}at/mcp, no key