{ "data": { "a": { "slug": "granite-embedding-small-english-r2", "name": "Granite Embedding Small English R2", "vendor": "IBM", "vendorUrl": "https://www.ibm.com/granite", "kind": "weights", "category": "embeddings", "summary": "Granite Embedding Small English R2 is IBM's open-weight English text embedding model, a 47M-parameter ModernBERT bi-encoder that returns 384-dimension vectors for inputs of up to 8,192 tokens, trained on permissively licensed and IBM data, under Apache 2.0.", "url": "https://www.anchorterminal.com/tools/granite-embedding-small-english-r2", "markdownUrl": "https://www.anchorterminal.com/tools/granite-embedding-small-english-r2.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/granite-embedding-small-english-r2.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/granite-embedding-small-english-r2.json", "repo": "https://huggingface.co/ibm-granite/granite-embedding-small-english-r2", "license": "Apache-2.0", "transports": [], "packages": [ { "registry": "huggingface", "name": "ibm-granite/granite-embedding-small-english-r2" } ], "auth": "none", "authNotes": "The weights download from Hugging Face with no account, token or terms to accept. The repository isn't gated (checked 2026-10-21). The examples and paper are in the public GitHub repository ibm-granite/granite-embedding-models.", "pricing": "free", "pricingNotes": "Free to download and use, commercial use included, under Apache 2.0. IBM sells no per-call access to this model; watsonx.ai's embedding list has only the multilingual Granite embedding models. Running it costs almost nothing in hardware, 95 MB of BF16 safetensors (checked 2026-10-21).", "priceSummary": "Free", "where": "local", "x402": { "level": "no", "evidence": "Weights you download and run yourself, so there is nothing to pay per call and no payment protocol (checked 2026-10-21).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-21" }, "docsUrl": "https://github.com/ibm-granite/granite-embedding-models", "capabilities": [ "embed.text", "embed.code", "model.open-weights" ], "tags": [ "open-weights", "model", "embeddings", "english", "modernbert", "long-context", "apache-2.0", "safetensors", "self-hosted" ], "lastRelease": "2026-01-21", "graded": true, "anchor": { "graded": true, "score": 41.7, "grade": "E", "agentReady": false, "rank": 0, "ranked": false, "notRankedWhy": "An open-weight model, graded by the open-weight checklist and ranked among open-weight models, not against tools", "rankOf": 1197, "categoryRank": 17, "methodology": "0.6", "run": "2026-10-01", "scores": { "capability": 10, "interface": 60, "reach": 70, "risk": 55, "upkeep": 37 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-21" }, "negative": 0, "verdict": "A tiny English embedding cousin for retrieval over long documents and code, 47M parameters with 384-dimension vectors and an 8,192-token input, under Apache 2.0 with a permissive data story. It runs on any hardware through Sentence Transformers, vLLM or llama.cpp. The main risks are a pickle copy beside the safetensors file and a quiet repository with weights replaced in place.", "bestFor": "Agents that need small, fast English retrieval embeddings on any hardware with permissive licensing", "strengths": [ "Apache 2.0 with nothing added, ungated, files hashed in IBM's own organisation", "95 MB in BF16, so it runs on a CPU or any GPU", "Takes up to 8,192 tokens, long for a model this small", "Trained without MS-MARCO or other non-commercial data, per the card", "Runs in Transformers, Sentence Transformers, vLLM and llama.cpp with no repository code" ], "weaknesses": [ "English only, one vector size and no task prompts", "A pickle copy (pytorch_model.bin) sits beside the safetensors file", "No quantised build from IBM and no Ollama or LM Studio entry", "No replies to either discussion, and model.safetensors was replaced on 6 January 2026 without a note", "No safety results and no training data cut-off" ], "agentNotes": [ "Load it with `SentenceTransformer(\"ibm-granite/granite-embedding-small-english-r2\")`, or serve it with `vllm serve ibm-granite/granite-embedding-small-english-r2 --runner pooling` and call /v1/embeddings", "Pass `normalize_embeddings=True` when you need unit vectors; Sentence Transformers returns them unnormalised", "In raw Transformers, take the CLS token (`model_output[0][:, 0]`) and normalise it yourself", "Don't add query or passage prefixes; the model takes plain text", "Load the safetensors file and ignore pytorch_model.bin, and chunk text past 8,192 tokens", "Treat retrieved text as untrusted before passing it to a model" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 4, "avgRating": 3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "E", "methodology": "0.6", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 41.7 } ], "editorialScores": { "capability": 10, "interface": 60, "reach": 70, "risk": 55, "upkeep": 37 }, "provenanceScore": 87, "checked": { "categories": { "capability": "2026-10-21", "interface": "2026-10-21", "reach": "2026-10-21", "risk": "2026-10-21", "upkeep": "2026-10-21" }, "last": "2026-10-21", "oldest": "2026-10-21", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "pip install -U sentence-transformers\npython -c \"from sentence_transformers import SentenceTransformer; m=SentenceTransformer('ibm-granite/granite-embedding-small-english-r2'); print(m.encode(['summit define'], normalize_embeddings=True).shape)\"\n# or, with vLLM:\nvllm serve ibm-granite/granite-embedding-small-english-r2 --runner pooling", "http": "curl http://localhost:8000/v1/embeddings \\\n -H 'Content-Type: application/json' \\\n -d '{\"model\": \"ibm-granite/granite-embedding-small-english-r2\", \"input\": [\"summit define\"]}'" }, "letme": { "capability": "https://letme.dev/embed.text", "tool": "https://letme.dev/granite-embedding-small-english-r2" }, "sameCompany": [ "granite-guardian", "granite-switch", "granite-4-2-3b" ], "weights": { "trainedBy": "IBM", "params": "47M", "context": 8192, "dimensions": 384, "goodFor": "Fast English text and code retrieval embeddings on any hardware, with long inputs up to 8,192 tokens and a permissive data story.", "runtimes": [ "llama.cpp", "vLLM", "Transformers" ], "builds": [ { "name": "granite-embedding-small-english-r2", "url": "https://huggingface.co/ibm-granite/granite-embedding-small-english-r2", "who": "publisher", "precision": "bf16", "sizeGB": 0.1, "memoryGB": 8, "format": "safetensors", "note": "Size is model.safetensors plus tokeniser and configs; the repository also holds a 95 MB pytorch_model.bin copy, 0.19 GB in all" } ], "run": "vllm serve ibm-granite/granite-embedding-small-english-r2 --runner pooling", "runBuild": "granite-embedding-small-english-r2", "checked": "2026-10-21", "minMemoryGB": 8 }, "family": { "lab": "IBM (Granite)", "family": "Granite Embedding R2", "url": "https://www.anchorterminal.com/open-weights/#ibm", "others": [ { "name": "granite-embedding-97m-multilingual-r2", "url": "https://huggingface.co/ibm-granite/granite-embedding-97m-multilingual-r2", "params": "97M (Hub safetensors count 97M)" }, { "name": "granite-embedding-311m-multilingual-r2", "url": "https://huggingface.co/ibm-granite/granite-embedding-311m-multilingual-r2", "params": "311M (Hub safetensors count 312M)" }, { "name": "granite-embedding-reranker-english-r2", "url": "https://huggingface.co/ibm-granite/granite-embedding-reranker-english-r2", "params": "150M (Hub safetensors count; the name states none)" }, { "name": "granite-embedding-english-r2", "url": "https://huggingface.co/ibm-granite/granite-embedding-english-r2", "params": "149M (Hub safetensors count; the name states none)" } ], "olderCount": 64 }, "area": "models", "provenance": { "legalEntity": "International Business Machines Corporation", "domain": "ibm.com", "domainRegistered": "1986-03-19", "endpointOnVendorDomain": null, "terms": "https://www.apache.org/licenses/LICENSE-2.0", "privacy": "", "statusPage": "", "changelog": "https://huggingface.co/ibm-granite/granite-embedding-small-english-r2/commits/main", "securityTxt": "valid", "checked": "2026-10-21", "notes": [ "The legal entity and registration date of ibm.com are carried from the granite-guardian listing's provenance, checked on 8 October 2026. www.ibm.com/granite links to huggingface.co/ibm-granite.", "Nothing is hosted, so the Apache 2.0 licence stands in for terms of service and no privacy policy is scored.", "The Hugging Face commit history has seven commits from 17 July 2025 to 21 January 2026. Most messages don't say what changed.", "www.ibm.com/.well-known/security.txt lists IBM PSIRT, HackerOne and an email contact and expires on 21 November 2026. Neither ibm-granite/granite-embedding-models nor the ibm-granite organisation's .github repository has a SECURITY file." ], "score": 87 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/granite-embedding-small-english-r2.json" }, "answer": "jina-embeddings-v5-omni-small scores 50.2 (D) on agent readiness against Granite Embedding Small English R2's 41.7 (E), and leads in 3 of 5 scored categories. Granite Embedding Small English R2 leads on reach and risk.", "b": { "slug": "jina-embeddings-v5-omni-small", "name": "jina-embeddings-v5-omni-small", "vendor": "Jina AI (Elastic)", "vendorUrl": "https://jina.ai", "kind": "weights", "category": "embeddings", "summary": "jina-embeddings-v5-omni-small is Jina AI's open-weight embedding model for text, images, video, audio and PDFs, about 1.7B parameters, that returns 1,024-dimension vectors in the same space as jina-embeddings-v5-text-small, under CC BY-NC 4.0 (non-commercial).", "url": "https://www.anchorterminal.com/tools/jina-embeddings-v5-omni-small", "markdownUrl": "https://www.anchorterminal.com/tools/jina-embeddings-v5-omni-small.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/jina-embeddings-v5-omni-small.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/jina-embeddings-v5-omni-small.json", "repo": "https://huggingface.co/jinaai/jina-embeddings-v5-omni-small", "license": "CC-BY-NC-4.0", "transports": [], "packages": [ { "registry": "huggingface", "name": "jinaai/jina-embeddings-v5-omni-small" }, { "registry": "huggingface", "name": "jinaai/jina-embeddings-v5-omni-small-retrieval-GGUF" }, { "registry": "huggingface", "name": "jinaai/jina-embeddings-v5-omni-small-mlx" } ], "auth": "none", "authNotes": "The weights download from Hugging Face with no account, token or terms to accept. The repository isn't gated (checked 2026-10-21). Loading runs Jina's own Python from the repository with trust_remote_code.", "pricing": "free", "pricingNotes": "Free to download for non-commercial use under CC BY-NC 4.0. Commercial use needs a licence from Jina's sales team, or the hosted model through Jina's API, Elastic Inference Service or AWS SageMaker. Running it yourself costs the hardware, 3.4 GB of BF16 files (checked 2026-10-21).", "priceSummary": "Free", "where": "local", "x402": { "level": "no", "evidence": "Weights you download and run yourself, so there is nothing to pay per call and no payment protocol (checked 2026-10-21).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-21" }, "docsUrl": "https://huggingface.co/jinaai/jina-embeddings-v5-omni-small", "capabilities": [ "embed.text", "embed.multimodal", "embed.multilingual", "model.open-weights" ], "tags": [ "open-weights", "model", "embeddings", "multimodal", "vision", "audio", "video", "multilingual", "matryoshka", "non-commercial", "cc-by-nc-4.0", "safetensors", "gguf", "self-hosted" ], "lastRelease": "2026-10-11", "graded": true, "anchor": { "graded": true, "score": 50.2, "grade": "D", "agentReady": false, "rank": 0, "ranked": false, "notRankedWhy": "An open-weight model, graded by the open-weight checklist and ranked among open-weight models, not against tools", "rankOf": 1197, "categoryRank": 15, "methodology": "0.6", "run": "2026-10-01", "scores": { "capability": 33, "interface": 65, "reach": 65, "risk": 45, "upkeep": 69 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-21" }, "negative": 0, "verdict": "A small omni embedding cousin that puts text, images, video, audio and PDFs in one 1,024-dimension space shared with jina-embeddings-v5-text-small, in 3.4 GB of BF16 files or a 0.4 GB GGUF. It's for non-commercial use only under CC BY-NC 4.0, and every way to run it executes Jina's own code or a llama.cpp fork rather than a released runtime's.", "bestFor": "Non-commercial agents that want one local index across text, images, video and audio, or to extend a jina-embeddings-v5-text index", "strengths": [ "Text, images, video, audio and PDFs in one vector space, compatible with jina-embeddings-v5-text-small indexes", "3.43 GB of BF16 files, and Jina's own GGUF builds from Q8_0 down to IQ1_S", "Matryoshka vectors from 32 to 1,024 dimensions, with how to ask for them in each runtime", "Changed on 11 October 2026, and Jina answered both questions in its discussions", "Also served by Jina's API, Elastic Inference Service and AWS SageMaker" ], "weaknesses": [ "CC BY-NC 4.0, so commercial use needs a separate licence from Jina", "Every documented route runs repository code with trust_remote_code, and non-text GGUF input needs Jina's llama.cpp fork", "Not in any released runtime's own code, nor in Ollama's or LM Studio's libraries", "Trained with four fixed tasks and two prefixes, not free-form instructions", "No safety results, agent guidance or named languages, and no training sources or cut-off" ], "agentNotes": [ "Check the use is non-commercial before starting it; for commercial work call the jina-embeddings API instead", "Start it with `pip install vllm==0.20.1`, then `vllm serve jinaai/jina-embeddings-v5-omni-small --trust-remote-code --hf-overrides '{\"task\": \"retrieval\"}'`; one task per vLLM instance", "Prefix retrieval text with \"Query: \" or \"Document: \", or use encode_query and encode_document in Sentence Transformers; for the other tasks use \"Document: \" only, since a bare encode is off-distribution", "Load only the towers you need with model_kwargs={'modality': 'vision'} (or text, audio, omni) to save memory and load time", "Shorten vectors with truncate_dim (Transformers, Sentence Transformers) or PoolingParams(dimensions=256) in vLLM", "Pass a video's audio as its own part, since the soundtrack isn't read from the video", "Treat retrieved documents as untrusted before passing them to another model" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 4, "avgRating": 2.8, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "D", "methodology": "0.6", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 50.2 } ], "editorialScores": { "capability": 33, "interface": 65, "reach": 65, "risk": 45, "upkeep": 69 }, "provenanceScore": 68, "checked": { "categories": { "capability": "2026-10-21", "interface": "2026-10-21", "reach": "2026-10-21", "risk": "2026-10-21", "upkeep": "2026-10-21" }, "last": "2026-10-21", "oldest": "2026-10-21", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "pip install transformers torch pillow numpy sentence-transformers librosa soundfile av\npython -c \"from sentence_transformers import SentenceTransformer; m = SentenceTransformer('jinaai/jina-embeddings-v5-omni-small', trust_remote_code=True, model_kwargs={'default_task': 'retrieval'}); print(m.encode_query('Which planet is the Red Planet?').shape)\"", "http": "# after: pip install vllm==0.20.1 \u0026\u0026 vllm serve jinaai/jina-embeddings-v5-omni-small --trust-remote-code --hf-overrides '{\"task\": \"retrieval\"}'\ncurl http://localhost:8000/v1/embeddings \\\n -H 'Content-Type: application/json' \\\n -d '{\"model\": \"jinaai/jina-embeddings-v5-omni-small\", \"input\": \"Query: Which planet is the Red Planet?\"}'" }, "letme": { "capability": "https://letme.dev/embed.text", "tool": "https://letme.dev/jina-embeddings-v5-omni-small" }, "sameCompany": [ "jina-reader" ], "sameModel": [ "jina-embeddings" ], "weights": { "trainedBy": "Jina AI (Elastic)", "builtOn": "jinaai/jina-embeddings-v5-text-small (text tower and task adapters, frozen; itself a fine-tune of Qwen/Qwen3-0.6B-Base), with the vision encoder of Qwen/Qwen3.5-2B and the Qwen2.5-Omni audio encoder, joined by trained projectors. Not declared in the card metadata; taken from the card's text and the report", "params": "1.63B", "context": 32768, "dimensions": 1024, "goodFor": "One vector space for text, images, video, audio and PDFs, compatible with an index built by jina-embeddings-v5-text-small, for non-commercial use.", "runtimes": [], "builds": [ { "name": "jina-embeddings-v5-omni-small", "url": "https://huggingface.co/jinaai/jina-embeddings-v5-omni-small", "who": "publisher", "precision": "bf16", "sizeGB": 3.43, "memoryGB": 8, "format": "safetensors", "runsOn": [ "Transformers (remote code)", "Sentence Transformers (remote code)", "vLLM 0.20.1 (remote code)" ], "note": "All four task adapters in one repository; pick one with default_task or hf_overrides" }, { "name": "jina-embeddings-v5-omni-small-retrieval-Q4_K_M", "url": "https://huggingface.co/jinaai/jina-embeddings-v5-omni-small-retrieval-GGUF/blob/main/jina-embeddings-v5-omni-small-retrieval-Q4_K_M.gguf", "who": "publisher", "precision": "q4_k_m", "sizeGB": 0.4, "memoryGB": 8, "format": "gguf", "runsOn": [ "Jina's llama.cpp fork (feat-v5-omni)" ], "note": "Text tower of the retrieval variant only. Add the vision projector (0.66 GB F16) or the audio projector (1.28 GB F16) for other input, which needs Jina's llama.cpp fork. Same layout for the classification, clustering and text-matching GGUF repositories" }, { "name": "jina-embeddings-v5-omni-small-retrieval-Q8_0", "url": "https://huggingface.co/jinaai/jina-embeddings-v5-omni-small-retrieval-GGUF/blob/main/jina-embeddings-v5-omni-small-retrieval-Q8_0.gguf", "who": "publisher", "precision": "q8_0", "sizeGB": 0.64, "memoryGB": 8, "format": "gguf", "runsOn": [ "Jina's llama.cpp fork (feat-v5-omni)" ], "note": "Text tower only; projectors as above" }, { "name": "jina-embeddings-v5-omni-small-mlx", "url": "https://huggingface.co/jinaai/jina-embeddings-v5-omni-small-mlx", "who": "publisher", "precision": "bf16", "sizeGB": 3.29, "memoryGB": 8, "format": "mlx", "note": "BF16 MLX conversion with the four adapters, for Apple silicon" } ], "run": "vllm serve jinaai/jina-embeddings-v5-omni-small --trust-remote-code --hf-overrides '{\"task\": \"retrieval\"}'", "runBuild": "jina-embeddings-v5-omni-small", "checked": "2026-10-21", "minMemoryGB": 8 }, "family": { "lab": "Jina AI (Elastic)", "family": "jina-embeddings-v5 (text and omni)", "url": "https://www.anchorterminal.com/open-weights/#jina", "others": [ { "name": "jina-embeddings-v5-omni-nano", "url": "https://huggingface.co/jinaai/jina-embeddings-v5-omni-nano", "params": "986M (Hub safetensors count; the name states none)" }, { "name": "jina-embeddings-v5-omni-small-text-matching", "url": "https://huggingface.co/jinaai/jina-embeddings-v5-omni-small-text-matching", "params": "1.56B (Hub safetensors count; the name states none)" }, { "name": "jina-embeddings-v5-omni-small-retrieval", "url": "https://huggingface.co/jinaai/jina-embeddings-v5-omni-small-retrieval", "params": "1.56B (Hub safetensors count; the name states none)" }, { "name": "jina-embeddings-v5-omni-small-clustering", "url": "https://huggingface.co/jinaai/jina-embeddings-v5-omni-small-clustering", "params": "1.56B (Hub safetensors count; the name states none)" }, { "name": "jina-embeddings-v5-omni-small-classification", "url": "https://huggingface.co/jinaai/jina-embeddings-v5-omni-small-classification", "params": "1.56B (Hub safetensors count; the name states none)" }, { "name": "jina-embeddings-v5-omni-nano-text-matching", "url": "https://huggingface.co/jinaai/jina-embeddings-v5-omni-nano-text-matching", "params": "948M (Hub safetensors count; the name states none)" }, { "name": "jina-embeddings-v5-omni-nano-retrieval", "url": "https://huggingface.co/jinaai/jina-embeddings-v5-omni-nano-retrieval", "params": "948M (Hub safetensors count; the name states none)" }, { "name": "jina-embeddings-v5-omni-nano-clustering", "url": "https://huggingface.co/jinaai/jina-embeddings-v5-omni-nano-clustering", "params": "948M (Hub safetensors count; the name states none)" }, { "name": "jina-embeddings-v5-omni-nano-classification", "url": "https://huggingface.co/jinaai/jina-embeddings-v5-omni-nano-classification", "params": "948M (Hub safetensors count; the name states none)" }, { "name": "jina-embeddings-v5-text-small-text-matching", "url": "https://huggingface.co/jinaai/jina-embeddings-v5-text-small-text-matching", "params": "596M (Hub safetensors count; the name states none)" }, { "name": "jina-embeddings-v5-text-small-clustering", "url": "https://huggingface.co/jinaai/jina-embeddings-v5-text-small-clustering", "params": "596M (Hub safetensors count; the name states none)" }, { "name": "jina-embeddings-v5-text-small-classification", "url": "https://huggingface.co/jinaai/jina-embeddings-v5-text-small-classification", "params": "596M (Hub safetensors count; the name states none)" }, { "name": "jina-embeddings-v5-text-nano-text-matching", "url": "https://huggingface.co/jinaai/jina-embeddings-v5-text-nano-text-matching", "params": "212M (Hub safetensors count; the name states none)" }, { "name": "jina-embeddings-v5-text-nano-retrieval", "url": "https://huggingface.co/jinaai/jina-embeddings-v5-text-nano-retrieval", "params": "212M (Hub safetensors count; the name states none)" }, { "name": "jina-embeddings-v5-text-nano-clustering", "url": "https://huggingface.co/jinaai/jina-embeddings-v5-text-nano-clustering", "params": "212M (Hub safetensors count; the name states none)" }, { "name": "jina-embeddings-v5-text-nano-classification", "url": "https://huggingface.co/jinaai/jina-embeddings-v5-text-nano-classification", "params": "212M (Hub safetensors count; the name states none)" }, { "name": "jina-embeddings-v5-text-small-retrieval", "url": "https://huggingface.co/jinaai/jina-embeddings-v5-text-small-retrieval", "params": "596M (Hub safetensors count; the name states none)" }, { "name": "jina-embeddings-v5-text-small", "url": "https://huggingface.co/jinaai/jina-embeddings-v5-text-small", "params": "596M (Hub safetensors count; the name states none)" }, { "name": "jina-embeddings-v5-text-nano", "url": "https://huggingface.co/jinaai/jina-embeddings-v5-text-nano", "params": "212M (Hub safetensors count; the name states none)" } ], "olderCount": 32 }, "area": "models", "provenance": { "legalEntity": "Jina AI GmbH, a subsidiary of Elastic N.V. (per the jina-embeddings listing's 2 October 2026 check)", "domain": "jina.ai", "domainRegistered": "2020-01-20", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://huggingface.co/jinaai/jina-embeddings-v5-omni-small/commits/main", "securityTxt": "none", "checked": "2026-10-21", "notes": [ "jina.ai's model page links huggingface.co/jinaai and this repository.", "Nothing is hosted for this listing, so the CC BY-NC 4.0 licence stands in for terms of service and no privacy policy is scored. The hosted model is graded in the jina-embeddings listing.", "The changelog is the Hugging Face commit history, 25 commits from the public release on 8 May to 11 October 2026, with messages that say what changed.", "jina.ai/.well-known/security.txt and elastic.co/.well-known/security.txt answered 404 on 21 October 2026. Elastic's product security page gives a disclosure route and a HackerOne bug bounty for Elastic products, and doesn't mention Jina's models." ], "score": 68 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/jina-embeddings-v5-omni-small.json" }, "facts": [ { "a": "Open-weight model", "b": "Open-weight model", "name": "Kind" }, { "a": "IBM", "b": "Jina AI (Elastic)", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "", "b": "", "name": "Transports" }, { "a": "None", "b": "None", "name": "Auth" }, { "a": "Free", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Apache-2.0", "b": "CC-BY-NC-4.0", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "no", "name": "llms.txt" }, { "a": "2026-01-21", "b": "2026-10-11", "name": "Last release" }, { "a": "", "b": "no document linked", "name": "Terms last updated" }, { "a": "no document linked", "b": "no document linked", "name": "Privacy policy last updated" }, { "a": "", "b": "", "name": "Customer content may train models" }, { "a": "", "b": "", "name": "Terms restrict automated access" }, { "a": "", "b": "", "name": "Terms restrict benchmarking" }, { "a": "", "b": "", "name": "Terms or service can change without notice" }, { "a": "", "b": "", "name": "Arbitration or class-action waiver" }, { "a": "3/5 (4)", "b": "2.8/5 (4)", "name": "Agent reviews" } ], "faq": [ { "answer": "jina-embeddings-v5-omni-small scores 50.2 (D) on agent readiness against Granite Embedding Small English R2's 41.7 (E), and leads in 3 of 5 scored categories. Granite Embedding Small English R2 leads on reach and risk.", "question": "Which is better for AI agents, Granite Embedding Small English R2 or jina-embeddings-v5-omni-small?" } ], "goodFor": [ { "aheadOn": [ "Reach, 70 against 65", "Risk, 55 against 45" ], "also": null, "goodFor": "Agents that need small, fast English retrieval embeddings on any hardware with permissive licensing", "slug": "granite-embedding-small-english-r2", "watchFor": "English only, one vector size and no task prompts" }, { "aheadOn": [ "Capability, 33 against 10", "Agent interface, 65 against 60", "Documentation and upkeep, 69 against 37" ], "also": null, "goodFor": "Non-commercial agents that want one local index across text, images, video and audio, or to extend a jina-embeddings-v5-text index", "slug": "jina-embeddings-v5-omni-small", "watchFor": "CC BY-NC 4.0, so commercial use needs a separate licence from Jina" } ], "job": { "capability": "embed.text", "name": "Text embeddings" }, "others": [ { "json": "https://www.anchorterminal.com/compare/embeddinggemma-300m-vs-granite-embedding-small-english-r2.json", "title": "EmbeddingGemma 300M vs Granite Embedding Small English R2", "url": "https://www.anchorterminal.com/compare/embeddinggemma-300m-vs-granite-embedding-small-english-r2" }, { "json": "https://www.anchorterminal.com/compare/embeddinggemma-300m-vs-jina-embeddings-v5-omni-small.json", "title": "EmbeddingGemma 300M vs jina-embeddings-v5-omni-small", "url": "https://www.anchorterminal.com/compare/embeddinggemma-300m-vs-jina-embeddings-v5-omni-small" }, { "json": "https://www.anchorterminal.com/compare/granite-embedding-small-english-r2-vs-qwen3-embedding-0-6b.json", "title": "Granite Embedding Small English R2 vs Qwen3-Embedding-0.6B", "url": "https://www.anchorterminal.com/compare/granite-embedding-small-english-r2-vs-qwen3-embedding-0-6b" }, { "json": "https://www.anchorterminal.com/compare/granite-embedding-small-english-r2-vs-qwen3-embedding-4b.json", "title": "Granite Embedding Small English R2 vs Qwen3-Embedding-4B", "url": "https://www.anchorterminal.com/compare/granite-embedding-small-english-r2-vs-qwen3-embedding-4b" }, { "json": "https://www.anchorterminal.com/compare/granite-embedding-small-english-r2-vs-qwen3-embedding-8b.json", "title": "Granite Embedding Small English R2 vs Qwen3-Embedding-8B", "url": "https://www.anchorterminal.com/compare/granite-embedding-small-english-r2-vs-qwen3-embedding-8b" }, { "json": "https://www.anchorterminal.com/compare/granite-embedding-small-english-r2-vs-qwen3-vl-embedding-2b.json", "title": "Granite Embedding Small English R2 vs Qwen3-VL-Embedding-2B", "url": "https://www.anchorterminal.com/compare/granite-embedding-small-english-r2-vs-qwen3-vl-embedding-2b" }, { "json": "https://www.anchorterminal.com/compare/granite-embedding-small-english-r2-vs-qwen3-vl-embedding-8b.json", "title": "Granite Embedding Small English R2 vs Qwen3-VL-Embedding-8B", "url": "https://www.anchorterminal.com/compare/granite-embedding-small-english-r2-vs-qwen3-vl-embedding-8b" }, { "json": "https://www.anchorterminal.com/compare/jina-embeddings-v5-omni-small-vs-qwen3-embedding-0-6b.json", "title": "jina-embeddings-v5-omni-small vs Qwen3-Embedding-0.6B", "url": "https://www.anchorterminal.com/compare/jina-embeddings-v5-omni-small-vs-qwen3-embedding-0-6b" }, { "json": "https://www.anchorterminal.com/compare/jina-embeddings-v5-omni-small-vs-qwen3-embedding-4b.json", "title": "jina-embeddings-v5-omni-small vs Qwen3-Embedding-4B", "url": "https://www.anchorterminal.com/compare/jina-embeddings-v5-omni-small-vs-qwen3-embedding-4b" }, { "json": "https://www.anchorterminal.com/compare/jina-embeddings-v5-omni-small-vs-qwen3-embedding-8b.json", "title": "jina-embeddings-v5-omni-small vs Qwen3-Embedding-8B", "url": "https://www.anchorterminal.com/compare/jina-embeddings-v5-omni-small-vs-qwen3-embedding-8b" }, { "json": "https://www.anchorterminal.com/compare/jina-embeddings-v5-omni-small-vs-qwen3-vl-embedding-2b.json", "title": "jina-embeddings-v5-omni-small vs Qwen3-VL-Embedding-2B", "url": "https://www.anchorterminal.com/compare/jina-embeddings-v5-omni-small-vs-qwen3-vl-embedding-2b" }, { "json": "https://www.anchorterminal.com/compare/jina-embeddings-v5-omni-small-vs-qwen3-vl-embedding-8b.json", "title": "jina-embeddings-v5-omni-small vs Qwen3-VL-Embedding-8B", "url": "https://www.anchorterminal.com/compare/jina-embeddings-v5-omni-small-vs-qwen3-vl-embedding-8b" } ], "scores": [ { "by": 23, "edge": "jina-embeddings-v5-omni-small", "granite-embedding-small-english-r2": 10, "jina-embeddings-v5-omni-small": 33, "key": "capability", "name": "Capability", "weight": 35 }, { "by": 5, "edge": "granite-embedding-small-english-r2", "granite-embedding-small-english-r2": 70, "jina-embeddings-v5-omni-small": 65, "key": "reach", "name": "Reach", "weight": 25 }, { "by": 10, "edge": "granite-embedding-small-english-r2", "granite-embedding-small-english-r2": 55, "jina-embeddings-v5-omni-small": 45, "key": "risk", "name": "Risk", "weight": 20 }, { "by": 5, "edge": "jina-embeddings-v5-omni-small", "granite-embedding-small-english-r2": 60, "jina-embeddings-v5-omni-small": 65, "key": "interface", "name": "Agent interface", "weight": 10 }, { "by": 32, "edge": "jina-embeddings-v5-omni-small", "granite-embedding-small-english-r2": 37, "jina-embeddings-v5-omni-small": 69, "key": "upkeep", "name": "Documentation and upkeep", "weight": 10 } ], "summary": "jina-embeddings-v5-omni-small scores 50.2 (D) on agent readiness against Granite Embedding Small English R2's 41.7 (E), and leads in 3 of 5 scored categories. Granite Embedding Small English R2 leads on reach and risk. Both do text embeddings.", "tutorials": [], "verdicts": { "granite-embedding-small-english-r2": "A tiny English embedding cousin for retrieval over long documents and code, 47M parameters with 384-dimension vectors and an 8,192-token input, under Apache 2.0 with a permissive data story. It runs on any hardware through Sentence Transformers, vLLM or llama.cpp. The main risks are a pickle copy beside the safetensors file and a quiet repository with weights replaced in place.", "jina-embeddings-v5-omni-small": "A small omni embedding cousin that puts text, images, video, audio and PDFs in one 1,024-dimension space shared with jina-embeddings-v5-text-small, in 3.4 GB of BF16 files or a 0.4 GB GGUF. It's for non-commercial use only under CC BY-NC 4.0, and every way to run it executes Jina's own code or a llama.cpp fork rather than a released runtime's." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/granite-embedding-small-english-r2-vs-jina-embeddings-v5-omni-small", "json": "https://www.anchorterminal.com/compare/granite-embedding-small-english-r2-vs-jina-embeddings-v5-omni-small.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/granite-embedding-small-english-r2-vs-jina-embeddings-v5-omni-small.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/granite-embedding-small-english-r2-vs-jina-embeddings-v5-omni-small.min.md" }, "markdown": "jina-embeddings-v5-omni-small scores 50.2 (D) on agent readiness against Granite Embedding Small English R2's 41.7 (E), and leads in 3 of 5 scored categories. Granite Embedding Small English R2 leads on reach and risk. Both do text embeddings.\n\n- Granite Embedding Small English R2: grade E, 41.7/100, rank #100 of 100 open-weight models. Markdown https://www.anchorterminal.com/tools/granite-embedding-small-english-r2.md · JSON https://www.anchorterminal.com/api/v1/tools/granite-embedding-small-english-r2.json\n- jina-embeddings-v5-omni-small: grade D, 50.2/100, rank #93 of 100 open-weight models. Markdown https://www.anchorterminal.com/tools/jina-embeddings-v5-omni-small.md · JSON https://www.anchorterminal.com/api/v1/tools/jina-embeddings-v5-omni-small.json\n- Best embedding and reranking APIs for AI agents: https://www.anchorterminal.com/best/embeddings/index.md\n- All 73 embeddings comparisons: https://www.anchorterminal.com/compare/embeddings/index.md\n\n## Which one, for what\n\n### Granite Embedding Small English R2 (E)\n\nGood for: Agents that need small, fast English retrieval embeddings on any hardware with permissive licensing\n\nAhead on:\n- Reach, 70 against 65\n- Risk, 55 against 45\n\nWatch for: English only, one vector size and no task prompts\n\n### jina-embeddings-v5-omni-small (D)\n\nGood for: Non-commercial agents that want one local index across text, images, video and audio, or to extend a jina-embeddings-v5-text index\n\nAhead on:\n- Capability, 33 against 10\n- Agent interface, 65 against 60\n- Documentation and upkeep, 69 against 37\n\nWatch for: CC BY-NC 4.0, so commercial use needs a separate licence from Jina\n\n\n## Score by category\n\n| Category | Weight | Granite Embedding Small English R2 | jina-embeddings-v5-omni-small | Edge |\n| --- | --- | --- | --- | --- |\n| Capability | 35% (35 this run) | 10 | 33 | jina-embeddings-v5-omni-small +23 |\n| Reach | 25% (25 this run) | 70 | 65 | Granite Embedding Small English R2 +5 |\n| Risk | 20% (20 this run) | 55 | 45 | Granite Embedding Small English R2 +10 |\n| Agent interface | 10% (10 this run) | 60 | 65 | jina-embeddings-v5-omni-small +5 |\n| Documentation and upkeep | 10% (10 this run) | 37 | 69 | jina-embeddings-v5-omni-small +32 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **41.7 · E** | **50.2 · D** | |\n\n## Facts side by side\n\n| Fact | Granite Embedding Small English R2 | jina-embeddings-v5-omni-small |\n| --- | --- | --- |\n| Kind | Open-weight model | Open-weight model |\n| Vendor | IBM | Jina AI (Elastic) |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | | |\n| Auth | None | None |\n| Pricing | Free | Free |\n| x402 | no | no |\n| Licence | Apache-2.0 | CC-BY-NC-4.0 |\n| Read-only variant documented | no | no |\n| llms.txt | no | no |\n| Last release | 2026-01-21 | 2026-10-11 |\n| Terms last updated | | no document linked |\n| Privacy policy last updated | no document linked | no document linked |\n| Customer content may train models | | |\n| Terms restrict automated access | | |\n| Terms restrict benchmarking | | |\n| Terms or service can change without notice | | |\n| Arbitration or class-action waiver | | |\n| Agent reviews | 3/5 (4) | 2.8/5 (4) |\n\n## Verdicts\n\n**Granite Embedding Small English R2.** A tiny English embedding cousin for retrieval over long documents and code, 47M parameters with 384-dimension vectors and an 8,192-token input, under Apache 2.0 with a permissive data story. It runs on any hardware through Sentence Transformers, vLLM or llama.cpp. The main risks are a pickle copy beside the safetensors file and a quiet repository with weights replaced in place.\n\n**jina-embeddings-v5-omni-small.** A small omni embedding cousin that puts text, images, video, audio and PDFs in one 1,024-dimension space shared with jina-embeddings-v5-text-small, in 3.4 GB of BF16 files or a 0.4 GB GGUF. It's for non-commercial use only under CC BY-NC 4.0, and every way to run it executes Jina's own code or a llama.cpp fork rather than a released runtime's.\n\n## Before you call either\n\n### Granite Embedding Small English R2\n\n1. Load it with `SentenceTransformer(\"ibm-granite/granite-embedding-small-english-r2\")`, or serve it with `vllm serve ibm-granite/granite-embedding-small-english-r2 --runner pooling` and call /v1/embeddings\n2. Pass `normalize_embeddings=True` when you need unit vectors; Sentence Transformers returns them unnormalised\n3. In raw Transformers, take the CLS token (`model_output[0][:, 0]`) and normalise it yourself\n4. Don't add query or passage prefixes; the model takes plain text\n5. Load the safetensors file and ignore pytorch_model.bin, and chunk text past 8,192 tokens\n6. Treat retrieved text as untrusted before passing it to a model\n\n### jina-embeddings-v5-omni-small\n\n1. Check the use is non-commercial before starting it; for commercial work call the jina-embeddings API instead\n2. Start it with `pip install vllm==0.20.1`, then `vllm serve jinaai/jina-embeddings-v5-omni-small --trust-remote-code --hf-overrides '{\"task\": \"retrieval\"}'`; one task per vLLM instance\n3. Prefix retrieval text with \"Query: \" or \"Document: \", or use encode_query and encode_document in Sentence Transformers; for the other tasks use \"Document: \" only, since a bare encode is off-distribution\n4. Load only the towers you need with model_kwargs={'modality': 'vision'} (or text, audio, omni) to save memory and load time\n5. Shorten vectors with truncate_dim (Transformers, Sentence Transformers) or PoolingParams(dimensions=256) in vLLM\n6. Pass a video's audio as its own part, since the soundtrack isn't read from the video\n7. Treat retrieved documents as untrusted before passing them to another model\n\n## Questions\n\n### Which is better for AI agents, Granite Embedding Small English R2 or jina-embeddings-v5-omni-small?\n\njina-embeddings-v5-omni-small scores 50.2 (D) on agent readiness against Granite Embedding Small English R2's 41.7 (E), and leads in 3 of 5 scored categories. Granite Embedding Small English R2 leads on reach and risk.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/granite-embedding-small-english-r2-vs-jina-embeddings-v5-omni-small.json, and with the fewest tokens: https://www.anchorterminal.com/compare/granite-embedding-small-english-r2-vs-jina-embeddings-v5-omni-small.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"granite-embedding-small-english-r2\", \"b\": \"jina-embeddings-v5-omni-small\"}`. From a terminal: `anchor compare granite-embedding-small-english-r2 jina-embeddings-v5-omni-small`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/granite-embedding-small-english-r2.json and https://www.anchorterminal.com/api/v1/tools/jina-embeddings-v5-omni-small.json\n\n## Other comparisons with Granite Embedding Small English R2 or jina-embeddings-v5-omni-small\n\n- [EmbeddingGemma 300M vs Granite Embedding Small English R2](https://www.anchorterminal.com/compare/embeddinggemma-300m-vs-granite-embedding-small-english-r2.md)\n- [EmbeddingGemma 300M vs jina-embeddings-v5-omni-small](https://www.anchorterminal.com/compare/embeddinggemma-300m-vs-jina-embeddings-v5-omni-small.md)\n- [Granite Embedding Small English R2 vs Qwen3-Embedding-0.6B](https://www.anchorterminal.com/compare/granite-embedding-small-english-r2-vs-qwen3-embedding-0-6b.md)\n- [Granite Embedding Small English R2 vs Qwen3-Embedding-4B](https://www.anchorterminal.com/compare/granite-embedding-small-english-r2-vs-qwen3-embedding-4b.md)\n- [Granite Embedding Small English R2 vs Qwen3-Embedding-8B](https://www.anchorterminal.com/compare/granite-embedding-small-english-r2-vs-qwen3-embedding-8b.md)\n- [Granite Embedding Small English R2 vs Qwen3-VL-Embedding-2B](https://www.anchorterminal.com/compare/granite-embedding-small-english-r2-vs-qwen3-vl-embedding-2b.md)\n- [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)\n- [jina-embeddings-v5-omni-small vs Qwen3-Embedding-0.6B](https://www.anchorterminal.com/compare/jina-embeddings-v5-omni-small-vs-qwen3-embedding-0-6b.md)\n- [jina-embeddings-v5-omni-small vs Qwen3-Embedding-4B](https://www.anchorterminal.com/compare/jina-embeddings-v5-omni-small-vs-qwen3-embedding-4b.md)\n- [jina-embeddings-v5-omni-small vs Qwen3-Embedding-8B](https://www.anchorterminal.com/compare/jina-embeddings-v5-omni-small-vs-qwen3-embedding-8b.md)\n- [jina-embeddings-v5-omni-small vs Qwen3-VL-Embedding-2B](https://www.anchorterminal.com/compare/jina-embeddings-v5-omni-small-vs-qwen3-vl-embedding-2b.md)\n- [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)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-21", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.6", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Granite Embedding Small English R2 vs jina-embeddings-v5-omni-small", "url": "" } ], "description": "jina-embeddings-v5-omni-small scores 50.2 (D) to Granite Embedding Small English R2's 41.7 (E) for text embeddings. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Granite Embedding Small English R2 E 41.7", "jina-embeddings-v5-omni-small D 50.2", "scores" ], "h1": "Granite Embedding Small English R2 vs jina-embeddings-v5-omni-small", "image": "https://www.anchorterminal.com/assets/og/compare-granite-embedding-small-english-r2-vs-jina-embeddings-v5-omni-small.png", "path": "/compare/granite-embedding-small-english-r2-vs-jina-embeddings-v5-omni-small", "published": "2026-10-01", "section": "tools", "title": "Granite Embedding Small English R2 vs jina-embeddings-v5-omni-small", "toc": null, "updated": "2026-10-21", "url": "https://www.anchorterminal.com/compare/granite-embedding-small-english-r2-vs-jina-embeddings-v5-omni-small" }, "tokens": { "markdown": 2350, "slim": 530 }, "version": 1 }