{"v":1,"id":"model:hf:jinaai/jina-embeddings-v5-text-nano-retrieval","slug":"model-jinaai-jina-embeddings-v5-text-nano-retrieval","kind":"model","category":"embedding","title":"jina-embeddings-v5-text-nano-retrieval","summary":"jina-embeddings-v5-text: Task-Targeted Embedding Distillation","source":{"provider":"hf","ref":"jinaai/jina-embeddings-v5-text-nano-retrieval","url":"https://huggingface.co/jinaai/jina-embeddings-v5-text-nano-retrieval","rev":"ac5d898c8d382b17167c33e5c8af644a3519b47d","fetchedAt":"2026-10-02T21:00:37.584Z","etag":"W/\"2224-5rOuTV8w2sF8P3D24HPEbrhizDg\""},"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":82453,"downloadsWeek":327838,"likes":19,"takenAt":"2026-10-02T21:00:37.584Z"},"tags":["llama.cpp","onnx","safetensors","gguf","eurobert","embedding","llama-cpp","jina-embeddings-v5","feature-extraction","mteb","vllm","sentence-transformers","sentence-similarity","custom_code","multilingual"],"pipeline":"sentence-similarity","links":{"github":"ggml-org/llama.cpp","npm":"node-llama-cpp"},"updatedAt":"2026-04-15T09:36:21.000Z","collectedAt":"2026-10-02T21:00:37.584Z","review":{"numbers":["82,453 downloads on Hugging Face","19 likes","license cc-by-nc-4.0","0.1 GB for v5-nano-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":"2026-10-02T21:00:37.584Z","http":200},"description":"### **jina-embeddings-v5-text**: Task-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-nano-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-small](https://huggingface.co/jinaai/jina-embeddings-v5-text-small), for better performance at a bigger size.\n\nTrained using a novel approach that combines distillation with task-specific contrastive losses, `jina-embeddings-v5-text-nano-retrieval` outperforms existing state-of-the-art models of similar size across diverse embedding benchmarks.\n| Feature | Value |\n| --- | --- |\n| Parameters | 239M |\n| Supported Tasks | `retrieval` |\n| Max Sequence Length | 8192 |\n| Embedding Dimension | 768 |\n| Matryoshka Dimensions | 32, 64, 128, 256, 512, 768 |\n| Pooling Strategy | Last-token pooling |\n| Base Model | jinaai/jina-embeddings-v5-text-nano |\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-transformers` interface, install this package…\n\nSource: https://huggingface.co/jinaai/jina-embeddings-v5-text-nano-retrieval","install":{"kind":"model","hfId":"jinaai/jina-embeddings-v5-text-nano-retrieval","gated":false,"format":"gguf","files":[{"name":"model.safetensors","size":423543712,"sha256":"e38cb1ff168a60c24d88f9664997ceaf49afcfd93275af1b7f850b23070bbe7d"},{"name":"onnx/model.onnx","size":90982,"sha256":"ad8244eea593ae8488cfd821a7d573aa51a350bc817702d6da99f3bccab24f49"},{"name":"onnx/model_fp16.onnx","size":91921,"sha256":"028918f8c20e4f858dfcdf41e950f24194862c25422fd2d0299286855b446f06"},{"name":"onnx/model_q4.onnx","size":129099,"sha256":"a44811eb61f90bfcc24720c04e774ce9f5dc1d1539fe32a814aa40b16efbaa1f"},{"name":"onnx/model_q4f16.onnx","size":130307,"quant":"F16","sha256":"2f139a9c44942032ef6fff72e792e67ed06dc15d9badef261cb99e0ec25054ca"},{"name":"onnx/model_quantized.onnx","size":131365,"sha256":"ac93a7417c216e5076e37da2b3599f7ef16513934098a477680440c09f735a08"},{"name":"v5-nano-retrieval-F16.gguf","size":431396128,"quant":"F16","sha256":"0c09e71f0bbcfceb06c44d56da2fdcee8b14b2e0d72b33e321ee2a7d7b350826"},{"name":"v5-nano-retrieval-IQ1_M.gguf","size":101703232,"quant":"IQ1_M","sha256":"0990f1569f4317bdd4a7b7c4e8a88da579f1a360d86655ad967f2dd5a2e75d33"},{"name":"v5-nano-retrieval-IQ1_S.gguf","size":99436096,"quant":"IQ1_S","sha256":"65115271dc63d78a2172386821574816e8b46cfdb7a51259bec5185fe5897f55"},{"name":"v5-nano-retrieval-IQ2_M.gguf","size":113702464,"quant":"IQ2_M","sha256":"24a6d6ecb1e23b28b0230c049a1a0186166b5da2caedbef7447b2950cea3ec0e"},{"name":"v5-nano-retrieval-IQ2_XXS.gguf","size":105481792,"quant":"IQ2_XXS","sha256":"18e63fbd8694a98ff365212fcf63f50de60d49414500da8fa12b70d0324f759e"},{"name":"v5-nano-retrieval-IQ4_NL.gguf","size":152405056,"quant":"IQ4_NL","sha256":"f243c19458bcd8162632b89bfeaf02b077b24c2d812e5ece1b73bd380732ba29"},{"name":"v5-nano-retrieval-IQ4_XS.gguf","size":148866112,"quant":"IQ4_XS","sha256":"6c53e3f56df187833a88a6b07953469653903e7ddc7d2bc5b926f16820e46199"},{"name":"v5-nano-retrieval-Q2_K.gguf","size":130176064,"quant":"Q2_K","sha256":"79dba23470b6c7b5a283a13ddff5d8a7c7c3b269d259bbb8202f9087509d7381"},{"name":"v5-nano-retrieval-Q3_K_M.gguf","size":143152192,"quant":"Q3_K_M","sha256":"191937158b1b0369ccdfb6214f24537c7ff955d2d5849712338ac085d8bb113b"},{"name":"v5-nano-retrieval-Q4_K_M.gguf","size":156966976,"quant":"Q4_K_M","sha256":"f50822244ba0c7a348c5455b99bb8a0afd182511e8a816888c5dc65d972e51d5"},{"name":"v5-nano-retrieval-Q5_K_M.gguf","size":168910912,"quant":"Q5_K_M","sha256":"46fbc0423862cb6a5d4ff776d885f349d2a87c36d821dd5630f9fa184c9b4b92"},{"name":"v5-nano-retrieval-Q5_K_S.gguf","size":166560832,"quant":"Q5_K_S","sha256":"6aaf456de892e5244b924bd8533a57fd509d27dfbdb0a74c250a5d92bdfb09c3"},{"name":"v5-nano-retrieval-Q6_K.gguf","size":181601344,"quant":"Q6_K","sha256":"cbbad17eeb1189c4f4706e6df89b5fbab17c72b7878a8a71a74fdb2a46f8d995"},{"name":"v5-nano-retrieval-Q8_0.gguf","size":232883776,"quant":"Q8_0","sha256":"86b6e6279e9b9e71389f02a082764a2ac2b15a50e37482c26f98d69092f12442"}],"totalBytes":2757360362,"suggestedFile":"v5-nano-retrieval-Q4_K_M.gguf","requirements":{"ramGb":1,"diskBytes":156966976,"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-nano-retrieval"}}