{"v":1,"id":"model:hf:jinaai/jina-embeddings-v5-omni-small-retrieval-GGUF","slug":"model-jinaai-jina-embeddings-v5-omni-small-retrieval-gguf","kind":"model","category":"embedding","title":"jina-embeddings-v5-omni-small-retrieval-GGUF","summary":"jina-embeddings-v5-omni-small-retrieval-GGUF: Retrieval-Targeted Omni Embedding (Small) — GGUF","source":{"provider":"hf","ref":"jinaai/jina-embeddings-v5-omni-small-retrieval-GGUF","url":"https://huggingface.co/jinaai/jina-embeddings-v5-omni-small-retrieval-GGUF","rev":"6bcd03c40b56717ec02ca4a26e9746da505b9ccf","fetchedAt":"2026-10-02T21:00:07.546Z","etag":"W/\"37db-HxR1+NCfwNx5xyDni0a8iZ/HujU\""},"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":2231,"downloadsWeek":327838,"likes":7,"takenAt":"2026-10-02T21:00:07.546Z"},"tags":["llama.cpp","gguf","embedding","qwen3","jina-embeddings-v5","feature-extraction","sentence-transformers","multimodal","vision","audio","video","vllm","llama-cpp","image-feature-extraction","audio-feature-extraction","video-feature-extraction","sentence-similarity","multilingual","conversational"],"pipeline":"feature-extraction","links":{"github":"ggml-org/llama.cpp","npm":"node-llama-cpp"},"updatedAt":"2026-05-12T20:42:53.000Z","collectedAt":"2026-10-02T21:00:07.546Z","review":{"numbers":["2,231 downloads on Hugging Face","7 likes","license cc-by-nc-4.0","0.4 GB for jina-embeddings-v5-omni-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":"2026-10-02T21:00:07.546Z","http":200},"description":"### **jina-embeddings-v5-omni-small-retrieval-GGUF**: Retrieval-Targeted Omni Embedding (Small) — GGUF\n\n[ArXiv](https://arxiv.org/abs/2605.08384) | [Blog](https://www.elastic.co/search-labs/blog/jina-embeddings-v5-omni-all-media-one-index)\n\n*Average score vs. parameter count across image (MIEB-Lite), video (MMEB-V), and audio (MAEB) benchmarks — `jina-v5-omni-nano` and `jina-v5-omni-small` define the open-weight frontier (Table 1 in the [ArXiv report](https://arxiv.org/abs/2605.08384)).*\n\n### Model Overview\n\nGGUF + multimodal-projector build of\n[`jinaai/jina-embeddings-v5-omni-small-retrieval`](https://huggingface.co/jinaai/jina-embeddings-v5-omni-small-retrieval) for\n[`llama.cpp`](https://github.com/ggml-org/llama.cpp). Accepts **text,\nimages, video, and audio** and produces 1024-dim embeddings in the\nsame vector space as the torch reference and as\n[`jinaai/jina-embeddings-v5-text-small-retrieval`](https://huggingface.co/jinaai/jina-embeddings-v5-text-small-retrieval) at the same task —\nindex with text and query with any modality, no reindexing. For a more compact alternative, see [`jinaai/jina-embeddings-v5-omni-nano-retrieval-GGUF`](https://huggingface.co/jinaai/jina-embeddings-v5-omni-nano-retrieval-GGUF).\n\nThis is the **retrieval-targeted** variant of the `jina-embeddings-v5-omni-small` GGUF family. The umbrella with all GGUF variants and cross-repo benchmarks is [`jina-ai/jina-embeddings-v5-omni-gguf`](https://github.com/jina-ai/jina-embeddings-v5-omni-gguf).\n\n| Feature | Value |\n| --- | --- |\n| Parameters | ~1.56B (text + vision + audio towers) |\n| Embedding Dimension | 1024 |\n| Supported Tasks | `retrieval` |\n| Max Sequence Length | 32768 |\n| Pooling Strategy | Last-token |\n| Supported Inputs | text, image, video, audio |\n| Supported File Types | images: `.jpg`, `.jpeg`, `.png`, `.gif`, `.webp`, `.bmp`, `.tif`, `.tiff`, `.avif`, `.heic`, `.svg`; video: `.mp4`, `.avi`, `.mov`…\n\nSource: https://huggingface.co/jinaai/jina-embeddings-v5-omni-small-retrieval-GGUF","install":{"kind":"model","hfId":"jinaai/jina-embeddings-v5-omni-small-retrieval-GGUF","gated":false,"format":"gguf","files":[{"name":"jina-embeddings-v5-omni-small-retrieval-F16.gguf","size":1197638976,"quant":"F16","sha256":"cddb89cc38388d70792a2c788e2f472c7df7ac1d0c44b6145a02dcb6d0758e24"},{"name":"jina-embeddings-v5-omni-small-retrieval-IQ1_M.gguf","size":215863424,"quant":"IQ1_M","sha256":"88f7aa88b08f6209c53b7b988b6f063835b18eb3f36d3a85b67fd219048e89ca"},{"name":"jina-embeddings-v5-omni-small-retrieval-IQ1_S.gguf","size":207827072,"quant":"IQ1_S","sha256":"ba6d5fcac45737d4e48d4bcdaae6de1769bd5ba02e5d0e4b5508abf9a0f09d82"},{"name":"jina-embeddings-v5-omni-small-retrieval-IQ2_M.gguf","size":264720512,"quant":"IQ2_M","sha256":"5b0cb9b3604d76f8a802b999d9a8ccef6cf43a77ee7124bcaeaa7b68c091a7ec"},{"name":"jina-embeddings-v5-omni-small-retrieval-IQ2_XXS.gguf","size":229257344,"quant":"IQ2_XXS","sha256":"97bb6004bd1b5519bc7f7dfe68b6a2d61e69fac299a54b915429fcbe617f434c"},{"name":"jina-embeddings-v5-omni-small-retrieval-IQ4_NL.gguf","size":381341760,"quant":"IQ4_NL","sha256":"ed100b7a7082116764de581c53c17ab333616213e7e2ebc08825e42e1f5cba8c"},{"name":"jina-embeddings-v5-omni-small-retrieval-IQ4_XS.gguf","size":367579200,"quant":"IQ4_XS","sha256":"96b32a02b3f286ff8417eba278e49091dc4e0adb5c1ede51b26a3dce15edf615"},{"name":"jina-embeddings-v5-omni-small-retrieval-Q2_K.gguf","size":296013888,"quant":"Q2_K","sha256":"5ad230fbe7a3a8ddfa2800727e79a689001814a6f73b7c820c09108fe6a1f847"},{"name":"jina-embeddings-v5-omni-small-retrieval-Q3_K_M.gguf","size":346902592,"quant":"Q3_K_M","sha256":"f6421691b90ae4b4fca0780fc0501ab68611e6f02754e7445f27ec6290c68ef1"},{"name":"jina-embeddings-v5-omni-small-retrieval-Q4_K_M.gguf","size":396480576,"quant":"Q4_K_M","sha256":"8016b9b1c279a8f149811c8b5ad5dd4c2f120150f473dd83b3ecc46ebf76105e"},{"name":"jina-embeddings-v5-omni-small-retrieval-Q5_K_M.gguf","size":444190784,"quant":"Q5_K_M","sha256":"6a83a18ffd7ce2e6b375fab269a721f2c6bc96687ba4902d026e727feaf0a467"},{"name":"jina-embeddings-v5-omni-small-retrieval-Q5_K_S.gguf","size":436392000,"quant":"Q5_K_S","sha256":"373d5ffb52c9c9548a1f887856e2356763f2b42527423fce00a94bbf6efdb982"},{"name":"jina-embeddings-v5-omni-small-retrieval-Q6_K.gguf","size":494882880,"quant":"Q6_K","sha256":"06bbe0c2d8139d6da18203e915e6ee36f9dabc51cb233e78773b802b2e4e102f"},{"name":"jina-embeddings-v5-omni-small-retrieval-Q8_0.gguf","size":639157376,"quant":"Q8_0","sha256":"8fd3a363dd158a67bd19708f86b4f678908ef320cb8302fcae102ba7ed7f7d9f"},{"name":"jina-embeddings-v5-omni-small-retrieval-audio-mmproj-F16.gguf","size":1281424768,"quant":"F16","sha256":"ff2833fcd945aa8c6e19034d94db469c2560d081142fb41d8cc1b56cc303ae56"},{"name":"jina-embeddings-v5-omni-small-retrieval-vision-mmproj-F16.gguf","size":659834176,"quant":"F16","sha256":"87f497f0272cd617b7700c8874e790882d31fbf03ce98ed8e24910f64d445dba"}],"totalBytes":7859507328,"suggestedFile":"jina-embeddings-v5-omni-small-retrieval-Q4_K_M.gguf","requirements":{"ramGb":1,"diskBytes":396480576,"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-omni-small-retrieval-GGUF"}}