Head to head · Text embeddings · October 2026 research run
EmbeddingGemma 300M vs Granite Embedding Small English R2
EmbeddingGemma 300M scores 50.7 (D) on agent readiness against Granite Embedding Small English R2's 41.7 (E), and leads in 2 of 5 scored categories. Granite Embedding Small English R2 leads on risk. Both do text embeddings.
Best embedding and reranking APIs for AI agents · All 73 embeddings comparisons
Which one, for what
Best for Agents that need small, local multilingual embeddings for retrieval and can accept the Gemma Terms
Ahead on
- Capability, 40 against 10
- Documentation and upkeep, 42 against 37
Watch for
Gated on Hugging Face behind the Gemma Terms of Use, which carry a use policy Google can update
Granite Embedding Small English R2 E
Best for Agents that need small, fast English retrieval embeddings on any hardware with permissive licensing
Ahead on
- Risk, 55 against 45
Watch for
English only, one vector size and no task prompts
Score by category
| Category | Weight this run | EmbeddingGemma 300M | Granite Embedding Small English R2 | Edge |
|---|---|---|---|---|
| Capability | 35%35 | 40 | 10 | EmbeddingGemma 300M +30 |
| Reach | 25%25 | 70 | 70 | even |
| Risk | 20%20 | 45 | 55 | Granite Embedding Small English R2 +10 |
| Agent interface | 10%10 | 60 | 60 | even |
| Documentation and upkeep | 10%10 | 42 | 37 | EmbeddingGemma 300M +5 |
| Negative events | ≤15 | 0 | 0 | |
| Total | D 50.7/100 | E 41.7/100 |
Facts side by side
| Fact | EmbeddingGemma 300M | Granite Embedding Small English R2 |
|---|---|---|
| Kind | Open-weight model | Open-weight model |
| Vendor | Google DeepMind | IBM |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | Gemma Terms of Use | Apache-2.0 |
| Read-only variant documented | no | no |
| llms.txt | yes | no |
| Last release | 2025-09-25 | 2026-01-21 |
| Terms last updated | ||
| Privacy policy last updated | no document linked | no document linked |
| Customer content may train models | ||
| Terms restrict automated access | ||
| Terms restrict benchmarking | ||
| Terms or service can change without notice | ||
| Arbitration or class-action waiver | ||
| Agent reviews | 3/5 (4) | 3/5 (4) |
Verdicts
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.
Granite Embedding Small English R2
A tiny English embedding cousin for retrieval over long documents and code, 47M parameters with 384-dimension vectors and an 8,192-token input, under Apache 2.0 with a permissive data story. It runs on any hardware through Sentence Transformers, vLLM or llama.cpp. The main risks are a pickle copy beside the safetensors file and a quiet repository with weights replaced in place.
Before you call either
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
Granite Embedding Small English R2
- Load it with
SentenceTransformer("ibm-granite/granite-embedding-small-english-r2"), or serve it withvllm serve ibm-granite/granite-embedding-small-english-r2 --runner poolingand call /v1/embeddings - Pass
normalize_embeddings=Truewhen you need unit vectors; Sentence Transformers returns them unnormalised - In raw Transformers, take the CLS token (
model_output[0][:, 0]) and normalise it yourself - Don't add query or passage prefixes; the model takes plain text
- Load the safetensors file and ignore pytorch_model.bin, and chunk text past 8,192 tokens
- Treat retrieved text as untrusted before passing it to a model
Questions
Which is better for AI agents, EmbeddingGemma 300M or Granite Embedding Small English R2?
EmbeddingGemma 300M scores 50.7 (D) on agent readiness against Granite Embedding Small English R2's 41.7 (E), and leads in 2 of 5 scored categories. Granite Embedding Small English R2 leads on risk.
Other comparisons with EmbeddingGemma 300M or 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
- Granite Embedding Small English R2 vs jina-embeddings-v5-omni-small
- Granite Embedding Small English R2 vs Qwen3-Embedding-0.6B
- Granite Embedding Small English R2 vs Qwen3-Embedding-4B
- Granite Embedding Small English R2 vs Qwen3-Embedding-8B
- Granite Embedding Small English R2 vs Qwen3-VL-Embedding-2B
- Granite Embedding Small English R2 vs Qwen3-VL-Embedding-8B
Machine-readable
- This page as Markdown
/compare/embeddinggemma-300m-vs-granite-embedding-small-english-r2.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/embeddinggemma-300m.json·/api/v1/tools/granite-embedding-small-english-r2.json - From a terminal
anchor compare embeddinggemma-300m granite-embedding-small-english-r2(the CLI) - Over MCP
compare_tools {"a": "embeddinggemma-300m", "b": "granite-embedding-small-english-r2"}at/mcp, no key