richardyoung/olmocr-2-7b-1025-gguf overview

{
  "metadata": {},
  "card_data": {
    "license": "apache-2.0",
    "base_model": "allenai/olmOCR-2-7B-1025",
    "tags": [
      "gguf",
      "quantized",
      "ocr",
      "vision-language-model",
      "qwen2.5-vl",
      "llama-cpp",
      "ollama",
      "document-understanding"
    ],
    "pipeline_tag": "image-text-to-text",
    "language": [
      "en"
    ],
    "frontmatter": {
      "license": "apache-2.0",
      "base_model": "allenai/olmOCR-2-7B-1025",
      "tags": [
        "gguf",
        "quantized",
        "ocr",
        "vision-language-model",
        "qwen2.5-vl",
        "llama-cpp",
        "ollama",
        "document-understanding"
      ],
      "pipeline_tag": "image-text-to-text",
      "language": [
        "en"
      ]
    },
    "hero_image_url": "",
    "summary": "GGUF quantized version of allenai/olmOCR-2-7B-1025 — Allen AI's state-of-the-art OCR vision-language model, optimized for **local inference** with llama.cpp and Ollama. olmOCR excels at extracting structured text from documents, PDFs, images, and handwriting — all running locally on your hardware.",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlicense: apache-2.0\nbase_model: allenai/olmOCR-2-7B-1025\ntags:\n  - gguf\n  - quantized\n  - ocr\n  - vision-language-model\n  - qwen2.5-vl\n  - llama-cpp\n  - ollama\n  - document-understanding\npipeline_tag: image-text-to-text\nlanguage:\n  - en\n---\n\n# olmOCR-2-7B-1025 (GGUF)\n\nGGUF quantized version of [allenai/olmOCR-2-7B-1025](https://huggingface.co/allenai/olmOCR-2-7B-1025) — Allen AI's state-of-the-art OCR vision-language model, optimized for **local inference** with llama.cpp and Ollama.\n\nolmOCR excels at extracting structured text from documents, PDFs, images, and handwriting — all running locally on your hardware.\n\n## Quick Start\n\n### With Ollama\n\n```bash\nollama run hf.co/richardyoung/olmOCR-2-7B-1025-GGUF\n```\n\n### With llama.cpp\n\n```bash\nhuggingface-cli download richardyoung/olmOCR-2-7B-1025-GGUF \\\n    --include \"*Q8_0*\" --local-dir ./models\n\n./llama-cli -m ./models/*Q8_0*.gguf \\\n    --image document.png \\\n    -p \"Extract all text from this document.\" \\\n    -ngl 99\n```\n\n## Why This Model?\n\n- **Best-in-class OCR**: olmOCR outperforms many commercial OCR solutions on academic benchmarks\n- **Local & private**: Process sensitive documents without sending them to cloud APIs\n- **Structured output**: Extracts text with layout awareness — tables, columns, headers\n- **GGUF format**: Runs on consumer hardware with llama.cpp (CPU or GPU)\n\n## Use Cases\n\n- Extract text from scanned PDFs and documents\n- Digitize handwritten notes\n- Process invoices, receipts, and forms locally\n- Build privacy-preserving document pipelines\n\n## Also Available\n\n- [olmOCR MLX 8-bit](https://hf.co/richardyoung/olmOCR-2-7B-1025-MLX-8bit) — Apple Silicon optimized\n- [olmOCR MLX 6-bit](https://hf.co/richardyoung/olmOCR-2-7B-1025-MLX-6bit) — Smaller footprint on Mac\n- [olmOCR MLX 4-bit](https://hf.co/richardyoung/olmOCR-2-7B-1025-MLX-4bit) — Minimum RAM on Mac\n\n## Other Models by richardyoung\n\n- **Abliterated/Uncensored models**: [Qwen2.5-7B](https://hf.co/richardyoung/Qwen2.5-7B-Instruct-abliterated-GGUF) | [Qwen3-14B](https://hf.co/richardyoung/Qwen3-14B-abliterated-GGUF) | [DeepSeek-R1-32B](https://hf.co/richardyoung/Deepseek-R1-Distill-Qwen-32b-uncensored) | [Qwen3-8B](https://hf.co/richardyoung/Qwen3-8B-Abliterated)\n- **MLX quantizations (Apple Silicon)**: [Kimi-K2 series](https://hf.co/richardyoung/Kimi-K2-Instruct-0905-MLX-4bit) | [olmOCR MLX](https://hf.co/richardyoung/olmOCR-2-7B-1025-MLX-4bit)\n- **OCR & Vision**: [olmOCR GGUF](https://hf.co/richardyoung/olmOCR-2-7B-1025-GGUF)\n- **Healthcare/Medical**: [Synthea 575K patients dataset](https://hf.co/datasets/richardyoung/synthea-575k-patients) | [CardioEmbed](https://hf.co/richardyoung/CardioEmbed)\n- **Research**: [LLM Instruction-Following Evaluation](https://hf.co/richardyoung/llm-instruction-following-paper) (arxiv:2510.18892)\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "quantized",
    "ocr",
    "vision-language-model",
    "qwen2.5-vl",
    "llama-cpp",
    "ollama",
    "document-understanding",
    "image-text-to-text",
    "en",
    "arxiv:2510.18892",
    "base_model:allenai/olmOCR-2-7B-1025",
    "base_model:quantized:allenai/olmOCR-2-7B-1025",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 3,
  "downloads": 294,
  "gated": false,
  "private": false,
  "last_modified": "2026-03-23T02:07:04.000Z",
  "created_at": "2025-10-24T20:48:31.000Z",
  "pipeline_tag": "image-text-to-text",
  "library_name": ""
}

{
  "_id": "68fbe61fe5470f7df4216221",
  "id": "richardyoung/olmOCR-2-7B-1025-GGUF",
  "modelId": "richardyoung/olmOCR-2-7B-1025-GGUF",
  "sha": "3a69963c7e89cf625b1c01daac22ccf371235f86",
  "createdAt": "2025-10-24T20:48:31.000Z",
  "lastModified": "2026-03-23T02:07:04.000Z",
  "author": "richardyoung",
  "downloads": 294,
  "likes": 3,
  "gated": false,
  "private": false,
  "pipeline_tag": "image-text-to-text",
  "library_name": "",
  "siblings_count": 4
}