octopusmegalopod/some-glmocr-ggufs overview

{
  "metadata": {},
  "card_data": {
    "base_model": [
      "zai-org/GLM-OCR"
    ],
    "pipeline_tag": "image-text-to-text",
    "frontmatter": {
      "base_model": [
        "zai-org/GLM-OCR"
      ],
      "pipeline_tag": "image-text-to-text"
    },
    "hero_image_url": "",
    "summary": "GLM-OCR converted for use with llama.cpp. As of b8094, it may crash in llama.cpp if flash-attn is on or certain backends are used (e.g: CPU). ~~Regrettably, does not seem to perform well for single CJK line texts out of the box. Or perhaps it expects the image in a specific resolution, due to its dependence on PaddleLayout.~~ GLM-OCR in llama.cpp behaves differently depending on the maximum context for some reason. Setting -c 2000 gives wrong outputs typically, for example. Whereas -c 9000 has produced much better results so far in my tests. So far in my tests:",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model:\n- zai-org/GLM-OCR\npipeline_tag: image-text-to-text\n---\n[GLM-OCR](https://huggingface.co/zai-org/GLM-OCR) converted for use with llama.cpp. As of b8094, it may crash in llama.cpp if `flash-attn` is on or certain backends are used (e.g: CPU).\n\n~~Regrettably, does not seem to perform well for single CJK line texts out of the box. Or perhaps it expects the image in a specific resolution, due to its dependence on PaddleLayout.~~\n\nGLM-OCR in llama.cpp behaves differently depending on the maximum context for some reason. Setting `-c 2000` gives wrong outputs typically, for example. Whereas `-c 9000` has produced much better results so far in my tests.\n\nSo far in my tests:\n- performs poorly on Korean horizontal text lines.\n- performs decently on Japanese horizontal text lines.\n- performs poorly on Japanese vertical text lines.\n- performs excellently on Chinese horizontal text lines.\n- relatively robust to quantization",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "image-text-to-text",
    "base_model:zai-org/GLM-OCR",
    "base_model:quantized:zai-org/GLM-OCR",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 1,
  "downloads": 451,
  "gated": false,
  "private": false,
  "last_modified": "2026-02-19T01:29:09.000Z",
  "created_at": "2026-02-18T21:47:46.000Z",
  "pipeline_tag": "image-text-to-text",
  "library_name": ""
}

{
  "_id": "69963382fb4584a79829750d",
  "id": "octopusmegalopod/some-glmocr-ggufs",
  "modelId": "octopusmegalopod/some-glmocr-ggufs",
  "sha": "318c473f8b924c4ccbd748d85ecc22a76d499c50",
  "createdAt": "2026-02-18T21:47:46.000Z",
  "lastModified": "2026-02-19T01:29:09.000Z",
  "author": "octopusmegalopod",
  "downloads": 451,
  "likes": 1,
  "gated": false,
  "private": false,
  "pipeline_tag": "image-text-to-text",
  "library_name": "",
  "siblings_count": 10
}