# EmbeddingGemma 300M vs Qwen3-VL-Embedding-2B

> Qwen3-VL-Embedding-2B scores 55.4 (C) to EmbeddingGemma 300M's 50.7 (D) for text embeddings. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/embeddinggemma-300m-vs-qwen3-vl-embedding-2b
- Markdown: https://www.anchorterminal.com/compare/embeddinggemma-300m-vs-qwen3-vl-embedding-2b.md (~2,150 tokens)
- Slim: https://www.anchorterminal.com/compare/embeddinggemma-300m-vs-qwen3-vl-embedding-2b.min.md (~480 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/embeddinggemma-300m-vs-qwen3-vl-embedding-2b.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key)
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)
- Updated: 2026-10-21

Qwen3-VL-Embedding-2B scores 55.4 (C) on agent readiness against EmbeddingGemma 300M's 50.7 (D), and leads in 3 of 5 scored categories. EmbeddingGemma 300M leads on documentation and upkeep. Both do text embeddings.

- EmbeddingGemma 300M: grade D, 50.7/100, rank #91 of 100 open-weight models. Markdown https://www.anchorterminal.com/tools/embeddinggemma-300m.md · JSON https://www.anchorterminal.com/api/v1/tools/embeddinggemma-300m.json
- Qwen3-VL-Embedding-2B: grade C, 55.4/100, rank #80 of 100 open-weight models. Markdown https://www.anchorterminal.com/tools/qwen3-vl-embedding-2b.md · JSON https://www.anchorterminal.com/api/v1/tools/qwen3-vl-embedding-2b.json
- Best embedding and reranking APIs for AI agents: https://www.anchorterminal.com/best/embeddings/index.md
- All 73 embeddings comparisons: https://www.anchorterminal.com/compare/embeddings/index.md

## Which one, for what

### EmbeddingGemma 300M (D)

Good for: Agents that need small, local multilingual embeddings for retrieval and can accept the Gemma Terms

Ahead on:
- Documentation and upkeep, 42 against 36

Watch for: Gated on Hugging Face behind the Gemma Terms of Use, which carry a use policy Google can update

### Qwen3-VL-Embedding-2B (C)

Good for: Agents that need local multimodal search over text, screenshots, images and video on a small GPU or CPU

Ahead on:
- Capability, 50 against 40
- Reach, 75 against 70
- Agent interface, 65 against 60

Watch for: No quantised build from Alibaba and nothing in Ollama's or LM Studio's own libraries


## Score by category

| Category | Weight | EmbeddingGemma 300M | Qwen3-VL-Embedding-2B | Edge |
| --- | --- | --- | --- | --- |
| Capability | 35% (35 this run) | 40 | 50 | Qwen3-VL-Embedding-2B +10 |
| Reach | 25% (25 this run) | 70 | 75 | Qwen3-VL-Embedding-2B +5 |
| Risk | 20% (20 this run) | 45 | 45 | even |
| Agent interface | 10% (10 this run) | 60 | 65 | Qwen3-VL-Embedding-2B +5 |
| Documentation and upkeep | 10% (10 this run) | 42 | 36 | EmbeddingGemma 300M +6 |
| Negative events | ≤15 | 0 | 0 | |
| **Total** | | **50.7 · D** | **55.4 · C** | |

## Facts side by side

| Fact | EmbeddingGemma 300M | Qwen3-VL-Embedding-2B |
| --- | --- | --- |
| Kind | Open-weight model | Open-weight model |
| Vendor | Google DeepMind | Alibaba (Qwen team) |
| 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 | 2026-04-16 |
| Terms last updated |  | no document linked |
| 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.

**Qwen3-VL-Embedding-2B.** A small multimodal embedding cousin that puts text, images, screenshots and video into one vector space, in 4.3 GB of BF16 files that fit any 8 GB machine, under plain Apache 2.0. It loads with Sentence Transformers, vLLM or SGLang. The main gaps are no quantised build from Alibaba, few publisher replies and no safety material.

## Before you call either

### EmbeddingGemma 300M

1. Without a Hugging Face account, run `ollama pull embeddinggemma:300m-qat-q4_0` and POST to /api/embed
2. Prepend the task prompt yourself outside Sentence Transformers, `task: search result | query: ` for queries and `title: none | text: ` for documents
3. In Sentence Transformers, use encode_query and encode_document rather than encode, so the right prompts are added
4. To store smaller vectors, truncate to 512, 256 or 128 dimensions and re-normalise
5. Run it in float32 or bfloat16, never float16
6. Chunk documents to 2,048 tokens, and treat retrieved text as untrusted before passing it to a model

### Qwen3-VL-Embedding-2B

1. Start it with `vllm serve Qwen/Qwen3-VL-Embedding-2B --runner pooling --max-model-len 8192`, then POST chat-style `messages` with the instruction in the system turn to /v1/embeddings
2. Or `pip install -U sentence-transformers` (5.4 or later) and `SentenceTransformer('Qwen/Qwen3-VL-Embedding-2B').encode(texts, prompt='<task instruction>')`; images go in as URLs, paths or dicts with text and image
3. Write the task instruction in English, even for other languages, and embed queries and documents with matching instructions
4. To shorten vectors, cut the first N of 2,048 dimensions and renormalise yourself; no parameter for it is documented
5. Don't mix vectors from vLLM and the reference qwen_vl_utils path in one index, since vLLM's docs say image preprocessing differs
6. Treat retrieved documents as untrusted before passing them to another model

## Questions

### Which is better for AI agents, EmbeddingGemma 300M or Qwen3-VL-Embedding-2B?

Qwen3-VL-Embedding-2B scores 55.4 (C) on agent readiness against EmbeddingGemma 300M's 50.7 (D), and leads in 3 of 5 scored categories. EmbeddingGemma 300M leads on documentation and upkeep.


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/embeddinggemma-300m-vs-qwen3-vl-embedding-2b.json, and with the fewest tokens: https://www.anchorterminal.com/compare/embeddinggemma-300m-vs-qwen3-vl-embedding-2b.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "embeddinggemma-300m", "b": "qwen3-vl-embedding-2b"}`. From a terminal: `anchor compare embeddinggemma-300m qwen3-vl-embedding-2b`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/embeddinggemma-300m.json and https://www.anchorterminal.com/api/v1/tools/qwen3-vl-embedding-2b.json

## Other comparisons with EmbeddingGemma 300M or Qwen3-VL-Embedding-2B

- [EmbeddingGemma 300M vs Granite Embedding Small English R2](https://www.anchorterminal.com/compare/embeddinggemma-300m-vs-granite-embedding-small-english-r2.md)
- [EmbeddingGemma 300M vs jina-embeddings-v5-omni-small](https://www.anchorterminal.com/compare/embeddinggemma-300m-vs-jina-embeddings-v5-omni-small.md)
- [EmbeddingGemma 300M vs Qwen3-Embedding-0.6B](https://www.anchorterminal.com/compare/embeddinggemma-300m-vs-qwen3-embedding-0-6b.md)
- [EmbeddingGemma 300M vs Qwen3-Embedding-4B](https://www.anchorterminal.com/compare/embeddinggemma-300m-vs-qwen3-embedding-4b.md)
- [EmbeddingGemma 300M vs Qwen3-Embedding-8B](https://www.anchorterminal.com/compare/embeddinggemma-300m-vs-qwen3-embedding-8b.md)
- [EmbeddingGemma 300M vs Qwen3-VL-Embedding-8B](https://www.anchorterminal.com/compare/embeddinggemma-300m-vs-qwen3-vl-embedding-8b.md)
- [Granite Embedding Small English R2 vs Qwen3-VL-Embedding-2B](https://www.anchorterminal.com/compare/granite-embedding-small-english-r2-vs-qwen3-vl-embedding-2b.md)
- [jina-embeddings-v5-omni-small vs Qwen3-VL-Embedding-2B](https://www.anchorterminal.com/compare/jina-embeddings-v5-omni-small-vs-qwen3-vl-embedding-2b.md)
- [Qwen3-Embedding-0.6B vs Qwen3-VL-Embedding-2B](https://www.anchorterminal.com/compare/qwen3-embedding-0-6b-vs-qwen3-vl-embedding-2b.md)
- [Qwen3-Embedding-4B vs Qwen3-VL-Embedding-2B](https://www.anchorterminal.com/compare/qwen3-embedding-4b-vs-qwen3-vl-embedding-2b.md)
- [Qwen3-Embedding-8B vs Qwen3-VL-Embedding-2B](https://www.anchorterminal.com/compare/qwen3-embedding-8b-vs-qwen3-vl-embedding-2b.md)
- [Qwen3-VL-Embedding-2B vs Qwen3-VL-Embedding-8B](https://www.anchorterminal.com/compare/qwen3-vl-embedding-2b-vs-qwen3-vl-embedding-8b.md)

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp