Jina Embeddings
Jina AIJina AI's text embedding line, from the v2 English and bilingual encoders through v3's task-LoRA multilingual model to the v5-text family released in early 2026. v5-text-small is a 677M Qwen3-0.6B-Base distillation of Qwen3-Embedding-4B scoring 67.7 on MMTEB across 119+ languages at 32K tokens, with retrieval, text-matching, clustering and classification adapters shipped separately for vLLM and ONNX. The weights are published on the Hub, but the current generation is non-commercial.
The v4 multimodal retriever carries a separate Qwen Research License inherited from Qwen2.5-VL-3B, which is why it and the v5-omni tier are treated as a distinct vision-language product rather than folded into this record. The vendor's GGUF and vLLM re-publishes are the same weights in another container and are excluded from the download count to avoid double-counting.
Openness
2 high confidence- weights
- open(ungated safetensors on the Hub across the v2, v3 and v5-text lines)
- data
- closed(no training corpus or construction scripts released
- code
- partial(trust_remote_code inference modules and ONNX/GGUF conversions ship with the repositories
- license
- Apache-2.0(OSI, and only the older v1 and v2 encoders)+CC-BY-NC-4.0(non-commercial
Jina's current text models are non-commercial: v3 and the v5-text line ship under CC-BY-NC-4.0, with commercial use routed to a sales conversation rather than granted. Only the older v1 and v2 encoders carry Apache-2.0, and because CC-BY-NC-4.0 governs what ships today, that is the license the score reflects.
- https://huggingface.co/api/models/jinaai/jina-embeddings-v3 recorded 2026-09-11
license cc-by-nc-4.0 in cardData; gated: false; private: false; model.safetensors and an onnx/ folder among the files.
- https://huggingface.co/api/models/jinaai/jina-embeddings-v5-text-small recorded 2026-09-11
license cc-by-nc-4.0 in cardData; gated: false; private: false; task adapter safetensors present, confirming the v5-text line ships on the same non-commercial terms as v3.
- https://huggingface.co/jinaai/jina-embeddings-v3/raw/main/README.md recorded 2026-09-11
Front matter reads license: cc-by-nc-4.0, and the License section says the model is licensed under CC BY-NC 4.0 beyond the AWS and Azure listings and directs commercial usage inquiries to contact sales. Training is described against the arXiv report with no corpus released; the usage sections ship inference code only, via trust_remote_code and ONNX.
- https://huggingface.co/jinaai/jina-embeddings-v4/raw/main/README.md recorded 2026-09-11
License section reads "This model was initially released under cc-by-nc-4.0 due to an error. The correct license is the Qwen Research License, as this model is derived from Qwen-2.5-VL-3B which is governed by that license."
- https://huggingface.co/jinaai/jina-embeddings-v5-text-small/raw/main/README.md recorded 2026-09-11
Front matter reads license: cc-by-nc-4.0 and the License section states the model is licensed under CC BY-NC 4.0 with commercial use routed to sales. Training and evaluation detail is deferred to arXiv 2602.15547 with no corpus released, and the usage sections cover inference only.
Adoption
4 high confidenceAdoption is measured as Hugging Face downloads across the jina-embeddings text checkpoints — v2, v3 and the v5-text line — excluding the multimodal v4 and v5-omni tier and the separate jina-clip, code-embeddings and colbert lines.
- https://huggingface.co/api/models/jinaai/jina-embeddings-v3 recorded 2026-09-11
downloads: 2151116; gated: false; private: false for jinaai/jina-embeddings-v3.
- https://huggingface.co/api/models/jinaai/jina-embeddings-v4 recorded 2026-09-11
downloads: 324909 for jinaai/jina-embeddings-v4.
- https://huggingface.co/api/models/jinaai/jina-embeddings-v5-text-small recorded 2026-09-11
downloads: 300461 for jinaai/jina-embeddings-v5-text-small.
Capability
4 high confidenceJina-embeddings-v5-text-small is current-generation, multilingual and long-context, scoring 67.7 on MMTEB against Harrier-OSS's 74.3 on the same benchmark — a step behind the category leader rather than level with it.
- https://huggingface.co/jinaai/jina-embeddings-v5-text-small/raw/main/README.md recorded 2026-09-11
Card states jina-embeddings-v5-text-small scores 71.7 average on MTEB English v2 and 67.7 on MMTEB with 677M parameters, the highest among multilingual embedding models under 1B, supporting 119+ languages at up to 32K tokens and built on Qwen3-0.6B-Base by distillation from Qwen3-Embedding-4B.
Verified 2026-09-11