# EmbeddingGemma 2 vs Qwen3-VL-Embedding-8B

> EmbeddingGemma 2 scores 66.4 (B) to Qwen3-VL-Embedding-8B's 62.1 (B) for text embeddings. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/embeddinggemma-2-vs-qwen3-vl-embedding-8b
- Markdown: https://www.anchorterminal.com/compare/embeddinggemma-2-vs-qwen3-vl-embedding-8b.md (~2,350 tokens)
- Slim: https://www.anchorterminal.com/compare/embeddinggemma-2-vs-qwen3-vl-embedding-8b.min.md (~580 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/embeddinggemma-2-vs-qwen3-vl-embedding-8b.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: 2026-10-30

EmbeddingGemma 2 scores 66.4 (B) on agent readiness against Qwen3-VL-Embedding-8B's 62.1 (B), and leads in 4 of 5 scored categories. Qwen3-VL-Embedding-8B leads on capability. Both do text embeddings.

- EmbeddingGemma 2: grade B, 66.4/100, rank #16 of 117 open-weight models. Markdown https://www.anchorterminal.com/tools/embeddinggemma-2.md · JSON https://www.anchorterminal.com/api/v1/tools/embeddinggemma-2.json
- Qwen3-VL-Embedding-8B: grade B, 62.1/100, rank #32 of 117 open-weight models. Markdown https://www.anchorterminal.com/tools/qwen3-vl-embedding-8b.md · JSON https://www.anchorterminal.com/api/v1/tools/qwen3-vl-embedding-8b.json
- Best embedding and reranking APIs for AI agents: https://www.anchorterminal.com/best/embeddings/index.md
- All 81 embeddings comparisons: https://www.anchorterminal.com/compare/embeddings/index.md

## Which one, for what

### EmbeddingGemma 2 (B)

Good for: Agents that need one small local embedding model for text, code, images, video and audio search

Ahead on:
- Reach, 75 against 65
- Risk, 60 against 45
- Agent interface, 70 against 65
- Documentation and upkeep, 80 against 41

Watch for: The card requires deployments to follow the Gemma Prohibited Use Policy, which Google can update

### Qwen3-VL-Embedding-8B (B)

Good for: Agents with a 24 GB GPU that need local retrieval across text, images, screenshots, visual documents and video in one index.

Ahead on:
- Capability, 75 against 59

Watch for: Only a 16.3 GB BF16 build, about 20 GB of memory, with no GGUF, FP8 or Ollama build


## Score by category

| Category | Weight | EmbeddingGemma 2 | Qwen3-VL-Embedding-8B | Edge |
| --- | --- | --- | --- | --- |
| Capability | 35% (35 this run) | 59 | 75 | Qwen3-VL-Embedding-8B +16 |
| Reach | 25% (25 this run) | 75 | 65 | EmbeddingGemma 2 +10 |
| Risk | 20% (20 this run) | 60 | 45 | EmbeddingGemma 2 +15 |
| Agent interface | 10% (10 this run) | 70 | 65 | EmbeddingGemma 2 +5 |
| Documentation and upkeep | 10% (10 this run) | 80 | 41 | EmbeddingGemma 2 +39 |
| Negative events | ≤15 | 0 | 0 | |
| **Total** | | **66.4 · B** | **62.1 · B** | |

## Facts side by side

| Fact | EmbeddingGemma 2 | Qwen3-VL-Embedding-8B |
| --- | --- | --- |
| 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 | Apache 2.0 | Apache-2.0 |
| Read-only variant documented | no | no |
| llms.txt | yes | no |
| Last release | 2026-10-28 | 2026-04-16 |
| Terms last updated | 2026-04-01 | no document linked |
| Privacy policy last updated | no document linked | no document linked |
| Customer content may train models | not found in the text |  |
| Terms restrict automated access | not found in the text |  |
| Terms restrict benchmarking | not found in the text |  |
| Terms or service can change without notice | not found in the text |  |
| Arbitration or class-action waiver | 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.

**Qwen3-VL-Embedding-8B.** A multimodal embedding cousin that puts text, images, screenshots and video in one vector space for visual document and video retrieval, under plain Apache 2.0. Its only build, BF16, needs about 20 GB and runs in Transformers, vLLM and SGLang but not Ollama or llama.cpp. The main risk is the publisher's script on the Transformers path.

## Before you call either

### EmbeddingGemma 2

1. 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
2. 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
3. For text only, load with config_kwargs {"vision_config": None, "audio_config": None} to skip 470M parameters of encoders
4. Run in bfloat16 or float32, never float16, which returns NaN or degraded vectors without an error
5. Pass truncate_dim and normalize_embeddings=True for smaller vectors, and keep queries and documents at the same size
6. Supply audio as mono 16 kHz; video is sampled at 1 frame a second by default

### Qwen3-VL-Embedding-8B

1. Simplest start is Sentence Transformers 5.4 or later, `SentenceTransformer('Qwen/Qwen3-VL-Embedding-8B')`, which applies the template and the default instruction and runs no repository code
2. To serve it, `vllm serve Qwen/Qwen3-VL-Embedding-8B --runner pooling`, then POST messages with a system instruction and image_url or text parts to /v1/embeddings; vLLM's docs say its video preprocessing differs slightly from Qwen's qwen_vl_utils
3. Put the task instruction in the system turn, and write it in English, as the card advises; the default is "Represent the user's input."
4. To shorten vectors, keep the first N of the 4,096 values and L2-normalise again; the card gives 64 as the floor, and the report says int8 vectors hold up while binary ones lose noticeably
5. For several images per input use the reference embedder in QwenLM/Qwen3-VL-Embedding's src, which is newer than the script in the Hugging Face repository
6. Keep inputs under 32K tokens; the reference embedder defaults to 8,192, 1,843,200 pixels per image and 64 frames per video
7. Treat retrieved screenshots and documents as untrusted, since text in an image can carry instructions to whatever model reads the results

## Questions

### Which is better for AI agents, EmbeddingGemma 2 or Qwen3-VL-Embedding-8B?

EmbeddingGemma 2 scores 66.4 (B) on agent readiness against Qwen3-VL-Embedding-8B's 62.1 (B), and leads in 4 of 5 scored categories. Qwen3-VL-Embedding-8B leads on capability.


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/embeddinggemma-2-vs-qwen3-vl-embedding-8b.json, and with the fewest tokens: https://www.anchorterminal.com/compare/embeddinggemma-2-vs-qwen3-vl-embedding-8b.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "embeddinggemma-2", "b": "qwen3-vl-embedding-8b"}`. From a terminal: `anchor compare embeddinggemma-2 qwen3-vl-embedding-8b`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/embeddinggemma-2.json and https://www.anchorterminal.com/api/v1/tools/qwen3-vl-embedding-8b.json

## Other comparisons with EmbeddingGemma 2 or Qwen3-VL-Embedding-8B

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