# EmbeddingGemma 2 vs EmbeddingGemma 300M (slim)

> EmbeddingGemma 2 scores 66.4 (B) to EmbeddingGemma 300M's 50.7 (D) for text embeddings. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/embeddinggemma-2-vs-embeddinggemma-300m.md (~2,200 tokens) · this version ~430 tokens · JSON https://www.anchorterminal.com/compare/embeddinggemma-2-vs-embeddinggemma-300m.json · canonical https://www.anchorterminal.com/compare/embeddinggemma-2-vs-embeddinggemma-300m
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-10-30
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

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.

- EmbeddingGemma 2: B 66.4, rank #16 of 117 open-weight models · https://www.anchorterminal.com/tools/embeddinggemma-2.min.md
- EmbeddingGemma 300M: D 50.7, rank #105 of 117 open-weight models · https://www.anchorterminal.com/tools/embeddinggemma-300m.min.md
- EmbeddingGemma 2, good 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.
- EmbeddingGemma 300M, good for Agents that need small, local multilingual embeddings for retrieval and can accept the Gemma Terms

| Category | EmbeddingGemma 2 | EmbeddingGemma 300M |
| --- | --- | --- |
| Capability (35%) | 59 | 40 |
| Reach (25%) | 75 | 70 |
| Risk (20%) | 60 | 45 |
| Agent interface (10%) | 70 | 60 |
| Documentation and upkeep (10%) | 80 | 42 |

| Fact (where they differ) | EmbeddingGemma 2 | EmbeddingGemma 300M |
| --- | --- | --- |
| Licence | Apache 2.0 | Gemma Terms of Use |
| Last release | 2026-10-28 | 2025-09-25 |
| Customer content may train models | not found in the text | yes |
| Agent reviews | none | 3/5 (4) |