# EmbeddingGemma 300M vs Granite Embedding Small English R2 (slim)

> EmbeddingGemma 300M scores 50.7 (D) to Granite Embedding Small English R2's 41.7 (E) for text embeddings. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/embeddinggemma-300m-vs-granite-embedding-small-english-r2.md (~2,200 tokens) · this version ~480 tokens · JSON https://www.anchorterminal.com/compare/embeddinggemma-300m-vs-granite-embedding-small-english-r2.json · canonical https://www.anchorterminal.com/compare/embeddinggemma-300m-vs-granite-embedding-small-english-r2
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-10-21
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

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.

- EmbeddingGemma 300M: D 50.7, rank #91 of 100 open-weight models · https://www.anchorterminal.com/tools/embeddinggemma-300m.min.md
- Granite Embedding Small English R2: E 41.7, rank #100 of 100 open-weight models · https://www.anchorterminal.com/tools/granite-embedding-small-english-r2.min.md
- EmbeddingGemma 300M, good 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.
- Granite Embedding Small English R2, good for Agents that need small, fast English retrieval embeddings on any hardware with permissive licensing Ahead on Risk, 55 against 45.

| Category | EmbeddingGemma 300M | Granite Embedding Small English R2 |
| --- | --- | --- |
| Capability (35%) | 40 | 10 |
| Reach (25%) | 70 | 70 |
| Risk (20%) | 45 | 55 |
| Agent interface (10%) | 60 | 60 |
| Documentation and upkeep (10%) | 42 | 37 |

| Fact (where they differ) | EmbeddingGemma 300M | Granite Embedding Small English R2 |
| --- | --- | --- |
| Vendor | Google DeepMind | IBM |
| Licence | Gemma Terms of Use | Apache-2.0 |
| llms.txt | yes | no |
| Last release | 2025-09-25 | 2026-01-21 |