{"v":1,"id":"model:hf:jinaai/jina-embeddings-v5-text-small-retrieval","slug":"model-jinaai-jina-embeddings-v5-text-small-retrieval","kind":"model","category":"embedding","title":"jina-embeddings-v5-text-small-retrieval","summary":"jina-embeddings-v5-text-small-retrieval: Retrieval-Targeted Embedding Distillation","source":{"provider":"hf","ref":"jinaai/jina-embeddings-v5-text-small-retrieval","url":"https://huggingface.co/jinaai/jina-embeddings-v5-text-small-retrieval","rev":"6856e76bb72982e58de0620458a4e8b3614da340","fetchedAt":"2026-10-02T21:00:34.559Z","etag":"W/\"407f-5Jg7fFgExaigh6FAuOcApNwcKwk\""},"author":{"name":"jinaai","url":"https://huggingface.co/jinaai"},"license":{"spdx":"cc-by-nc-4.0","raw":"cc-by-nc-4.0","open":false,"note":"restricted license: terms at the source apply"},"metrics":{"downloads":111301,"downloadsWeek":327838,"likes":30,"takenAt":"2026-10-02T21:00:34.559Z"},"tags":["llama.cpp","onnx","safetensors","gguf","qwen3","embedding","llama-cpp","jina-embeddings-v5","feature-extraction","mteb","vllm","sentence-transformers","sentence-similarity","multilingual","text-embeddings-inference","conversational"],"pipeline":"sentence-similarity","links":{"github":"ggml-org/llama.cpp","npm":"node-llama-cpp"},"updatedAt":"2026-04-15T09:39:05.000Z","collectedAt":"2026-10-02T21:00:34.559Z","review":{"numbers":["111,301 downloads on Hugging Face","30 likes","license cc-by-nc-4.0","0.4 GB for v5-small-retrieval-Q4_K_M.gguf","327,838 npm downloads a week for node-llama-cpp","latest node-llama-cpp@3.22.1"],"log":null},"trust":"unlabeled","health":{"status":"alive","checkedAt":"2026-10-02T21:00:34.559Z","http":200},"description":"### **jina-embeddings-v5-text-small-retrieval**: Retrieval-Targeted Embedding Distillation\n\n[Elastic Inference Service](https://www.elastic.co/docs/explore-analyze/elastic-inference/eis) | [ArXiv](https://arxiv.org/abs/2602.15547) | [Release Note](https://jina.ai/news/jina-embeddings-v5-text-distilling-4b-quality-into-sub-1b-multilingual-embeddings) | [Blog](https://www.elastic.co/search-labs/blog/jina-embeddings-v5-text)\n\n### Model Overview\n\n`jina-embeddings-v5-text-small-retrieval` is a compact, high-performance text embedding model designed for information retrieval.\n\nIt is part of the **jina-embeddings-v5-text** model family, which also includes [jina-embeddings-v5-text-nano](https://huggingface.co/jinaai/jina-embeddings-v5-text-nano), a smaller model for more resource-constrained use cases.\n\nTrained using a novel approach that combines distillation with task-specific contrastive losses, `jina-embeddings-v5-text-small-retrieval` outperforms existing state-of-the-art models of similar size across diverse embedding benchmarks.\n| Feature | Value |\n| --- | --- |\n| Parameters | 677M |\n| Supported Tasks | `retrieval`|\n| Max Sequence Length | 32768 |\n| Embedding Dimension | 1024 |\n| Matryoshka Dimensions | 32, 64, 128, 256, 512, 768, 1024 |\n| Pooling Strategy | Last-token pooling |\n| Base Model | jinaai/jina-embeddings-v5-text-small |\n\n### Training and Evaluation\n\nFor training details and evaluation results, see our [technical report](https://arxiv.org/abs/2602.15547).\n\n### Usage\n\n  Requirements\n\nThe following Python packages are required:\n\n- `transformers>=5.1.0`\n- `torch>=2.8.0`\n- `peft>=0.15.2`\n- `vllm>=0.15.1`\n\n### Optional / Recommended\n- **flash-attention**: Installing [flash-attention](https://github.com/Dao-AILab/flash-attention) is recommended for improved inference speed and efficiency, but not mandatory.\n- **sentence-transformers**: If you want to use the model via the `sentence-…\n\nSource: https://huggingface.co/jinaai/jina-embeddings-v5-text-small-retrieval","install":{"kind":"model","hfId":"jinaai/jina-embeddings-v5-text-small-retrieval","gated":false,"format":"gguf","files":[{"name":"model.safetensors","size":1192133232,"sha256":"0362107c2b13e18284c5152c4d4f667a4dec4665abdfe4f5e43a9bb799ba2276"},{"name":"onnx/model.onnx","size":1266078,"sha256":"463fb3fec2adf9c47a946626dc2a0884e43091f95466083fb1754950000a7c1a"},{"name":"v5-small-retrieval-F16.gguf","size":1198182464,"quant":"F16","sha256":"98e84d9a7603122b6ff21d8ee18a924a96706dc65dd0b40c0399ec2ce9a80653"},{"name":"v5-small-retrieval-IQ1_M.gguf","size":216052096,"quant":"IQ1_M","sha256":"468b4acf9f9bf593d72b5c3a5c67dcdb50ab459e7135f5cb22c6105d4a7ad963"},{"name":"v5-small-retrieval-IQ1_S.gguf","size":208015744,"quant":"IQ1_S","sha256":"6a20696ea891e83dc3f6458bb06dcd46c3179dd809ce14205920399265b3e691"},{"name":"v5-small-retrieval-IQ2_M.gguf","size":264909184,"quant":"IQ2_M","sha256":"e84f5afc5e6b75005693420c8c9cfde01d8794226d55260592ed7bb0417069fb"},{"name":"v5-small-retrieval-IQ2_XXS.gguf","size":229446016,"quant":"IQ2_XXS","sha256":"7cd212ecf18f48dfba3820552b347e6a14630c192c0628fc29c5fe65451ea11c"},{"name":"v5-small-retrieval-IQ4_NL.gguf","size":381566336,"quant":"IQ4_NL","sha256":"c32c4796810e514ec87af949bde6a88bb8d634eb0020d1e7e61d3493c8cb1588"},{"name":"v5-small-retrieval-IQ4_XS.gguf","size":367803776,"quant":"IQ4_XS","sha256":"619371d1113f7af73ebde9bea8668c81e799e16404eed565bc4663598e5224a9"},{"name":"v5-small-retrieval-Q2_K.gguf","size":296238464,"quant":"Q2_K","sha256":"df29c1f962433e94e32b1e8f151dc3b9c693bddeb91390f67cf53b0adc4d1ba7"},{"name":"v5-small-retrieval-Q3_K_M.gguf","size":347127168,"quant":"Q3_K_M","sha256":"7819b1c9b5ffbf7535cc3d74dfeef0a62dbb35d24545eb8852e046f7714c033f"},{"name":"v5-small-retrieval-Q4_K_M.gguf","size":396705152,"quant":"Q4_K_M","sha256":"9440cf89f3e8a7a31a42e11b87e106dd5b344af4e0e3b6b21a96136cc8686e21"},{"name":"v5-small-retrieval-Q5_K_M.gguf","size":444415360,"quant":"Q5_K_M","sha256":"a0780ce70c26a89122ab2dd1e65f5a0cb4180f6654de1878f89b0a97420b1138"},{"name":"v5-small-retrieval-Q5_K_S.gguf","size":436616576,"quant":"Q5_K_S","sha256":"2ea3bbd03f528b544f8f6c34746bb5ccc79e601b98985b49861b5fe9f7e06d42"},{"name":"v5-small-retrieval-Q6_K.gguf","size":495107456,"quant":"Q6_K","sha256":"df15469cdb714253948a67ef6b125ea3a8514f1b9f90ee7b921576f3c9919304"},{"name":"v5-small-retrieval-Q8_0.gguf","size":639447424,"quant":"Q8_0","sha256":"b759677362414e664160ffb017fbc74c300feaa4ad4085f69f2cc1bfa12ccb71"}],"totalBytes":7115032526,"suggestedFile":"v5-small-retrieval-Q4_K_M.gguf","requirements":{"ramGb":1,"diskBytes":396705152,"note":"estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models"},"runWith":["llama.cpp"],"command":"lsh models install hf:jinaai/jina-embeddings-v5-text-small-retrieval"}}