second-state/jina-embeddings-v3-gguf overview

{
  "metadata": {},
  "card_data": {
    "base_model": "jinaai/jina-embeddings-v3",
    "model_creator": "jinaai",
    "quantized_by": "Second State Inc.",
    "frontmatter": {
      "base_model": "jinaai/jina-embeddings-v3",
      "model_creator": "jinaai",
      "quantized_by": "Second State Inc."
    },
    "hero_image_url": "https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg",
    "summary": "",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: jinaai/jina-embeddings-v3\nmodel_creator: jinaai\nquantized_by: Second State Inc.\n---\n\n<!-- header start -->\n<!-- 200823 -->\n<div style=\"width: auto; margin-left: auto; margin-right: auto\">\n<img src=\"https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg\" style=\"width: 100%; min-width: 400px; display: block; margin: auto;\">\n</div>\n<hr style=\"margin-top: 1.0em; margin-bottom: 1.0em;\">\n<!-- header end -->\n\n# jina-embeddings-v3-Embedding-GGUF\n\n## Original Model\n\n[jinaai/jina-embeddings-v3](https://huggingface.co/jinaai/jina-embeddings-v3)\n\n## Run with LlamaEdge\n\n- LlamaEdge version: coming soon\n\n<!-- - LlamaEdge version: [v0.14.17](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.14.17) -->\n\n- Prompt template\n\n  - Prompt type: `embedding`\n\n- Embedding size: `32, 64, 128, 256, 512, 768, 1024`\n\n- Run as LlamaEdge service\n\n  ```bash\n  wasmedge --dir .:. --nn-preload default:GGML:AUTO:jina-embeddings-v3-f16.gguf \\\n    llama-api-server.wasm \\\n    --prompt-template embedding \\\n    --ctx-size 768 \\\n    --model-name jina-embeddings-v3\n  ```\n<!-- \n## Quantized GGUF Models\n\n| Name | Quant method | Bits | Size | Use case |\n| ---- | ---- | ---- | ---- | ----- |\n| [jina-embeddings-v3-Q2_K.gguf](https://huggingface.co/second-state/jina-embeddings-v3-Embedding-GGUF/blob/main/jina-embeddings-v3-Q2_K.gguf)     | Q2_K   | 2 | 60.8 MB| smallest, significant quality loss - not recommended for most purposes |\n| [jina-embeddings-v3-Q3_K_L.gguf](https://huggingface.co/second-state/jina-embeddings-v3-Embedding-GGUF/blob/main/jina-embeddings-v3-Q3_K_L.gguf) | Q3_K_L | 3 | 80.6 MB| small, substantial quality loss |\n| [jina-embeddings-v3-Q3_K_M.gguf](https://huggingface.co/second-state/jina-embeddings-v3-Embedding-GGUF/blob/main/jina-embeddings-v3-Q3_K_M.gguf) | Q3_K_M | 3 | 76.2 MB| very small, high quality loss |\n| [jina-embeddings-v3-Q3_K_S.gguf](https://huggingface.co/second-state/jina-embeddings-v3-Embedding-GGUF/blob/main/jina-embeddings-v3-Q3_K_S.gguf) | Q3_K_S | 3 | 68.7 MB| very small, high quality loss |\n| [jina-embeddings-v3-Q4_0.gguf](https://huggingface.co/second-state/jina-embeddings-v3-Embedding-GGUF/blob/main/jina-embeddings-v3-Q4_0.gguf)     | Q4_0   | 4 | 83.7 MB| legacy; small, very high quality loss - prefer using Q3_K_M |\n| [jina-embeddings-v3-Q4_K_M.gguf](https://huggingface.co/second-state/jina-embeddings-v3-Embedding-GGUF/blob/main/jina-embeddings-v3-Q4_K_M.gguf) | Q4_K_M | 4 | 90.0 MB| medium, balanced quality - recommended |\n| [jina-embeddings-v3-Q4_K_S.gguf](https://huggingface.co/second-state/jina-embeddings-v3-Embedding-GGUF/blob/main/jina-embeddings-v3-Q4_K_S.gguf) | Q4_K_S | 4 | 84.0 MB| small, greater quality loss |\n| [jina-embeddings-v3-Q5_0.gguf](https://huggingface.co/second-state/jina-embeddings-v3-Embedding-GGUF/blob/main/jina-embeddings-v3-Q5_0.gguf)     | Q5_0   | 5 | 97.9 MB| legacy; medium, balanced quality - prefer using Q4_K_M |\n| [jina-embeddings-v3-Q5_K_M.gguf](https://huggingface.co/second-state/jina-embeddings-v3-Embedding-GGUF/blob/main/jina-embeddings-v3-Q5_K_M.gguf) | Q5_K_M | 5 | 103 MB| large, very low quality loss - recommended |\n| [jina-embeddings-v3-Q5_K_S.gguf](https://huggingface.co/second-state/jina-embeddings-v3-Embedding-GGUF/blob/main/jina-embeddings-v3-Q5_K_S.gguf) | Q5_K_S | 5 | 97.9 MB| large, low quality loss - recommended |\n| [jina-embeddings-v3-Q6_K.gguf](https://huggingface.co/second-state/jina-embeddings-v3-Embedding-GGUF/blob/main/jina-embeddings-v3-Q6_K.gguf)     | Q6_K   | 6 | 113 MB| very large, extremely low quality loss |\n| [jina-embeddings-v3-Q8_0.gguf](https://huggingface.co/second-state/jina-embeddings-v3-Embedding-GGUF/blob/main/jina-embeddings-v3-Q8_0.gguf)     | Q8_0   | 8 | 146 MB| very large, extremely low quality loss - not recommended |\n| [jina-embeddings-v3-f16.gguf](https://huggingface.co/second-state/jina-embeddings-v3-Embedding-GGUF/blob/main/jina-embeddings-v3-f16.gguf)       | f16   | 16 | 274 MB| very large, extremely low quality loss - not recommended |\n -->\n*Quantized with llama.cpp b6311*",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "custom_code",
    "base_model:jinaai/jina-embeddings-v3",
    "base_model:quantized:jinaai/jina-embeddings-v3",
    "endpoints_compatible",
    "region:us",
    "feature-extraction"
  ],
  "likes": 2,
  "downloads": 747,
  "gated": false,
  "private": false,
  "last_modified": "2025-08-29T02:14:06.000Z",
  "created_at": "2025-08-28T15:01:19.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "68b06f3f09f8c2b6852a5f5a",
  "id": "second-state/jina-embeddings-v3-GGUF",
  "modelId": "second-state/jina-embeddings-v3-GGUF",
  "sha": "61b5399b6dab4af55fd305574625d88f50241ca8",
  "createdAt": "2025-08-28T15:01:19.000Z",
  "lastModified": "2025-08-29T02:14:06.000Z",
  "author": "second-state",
  "downloads": 747,
  "likes": 2,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 21
}