gguf-org/ltx2.3-gguf overview

{
  "metadata": {},
  "card_data": {
    "license": "other",
    "license_name": "ltx-2-community-license-agreement",
    "license_link": "https://github.com/Lightricks/LTX-2/blob/main/LICENSE",
    "base_model": [
      "Lightricks/LTX-2.3"
    ],
    "frontmatter": {
      "license": "other",
      "license_name": "ltx-2-community-license-agreement",
      "license_link": "https://github.com/Lightricks/LTX-2/blob/main/LICENSE",
      "base_model": [
        "Lightricks/LTX-2.3"
      ]
    },
    "hero_image_url": "https://raw.githubusercontent.com/calcuis/gguf-pack/master/ltxv2.3.png",
    "summary": "## ltx2.3-gguf !screenshot see picture above for setup (inside sub-graph) btw, replace the ltx2.3-22b-dev or -distill with this universal checkpoint clip (see below) note: you don't need any extra node for running ltx2.3 under this setting; probably run it with beginner level gpu without problem, just wait slightly longer; you might need protobuf for rebuilding the tokenizer if you opt gemma3 gguf, simply install it with: `` .\\python_embeded\\python.exe -s -m pip install protobuf ``   demo",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlicense: other\nlicense_name: ltx-2-community-license-agreement\nlicense_link: https://github.com/Lightricks/LTX-2/blob/main/LICENSE\nbase_model:\n- Lightricks/LTX-2.3\n---\n## ltx2.3-gguf\n\n![screenshot](https://raw.githubusercontent.com/calcuis/gguf-pack/master/ltxv2.3.png)\n\nsee picture above for setup (inside sub-graph)\n- pull `ltx2.3-22b-dev-iq4_xs.gguf` to `diffusion_models`\n- pull `ltx2.3_text_encoder_projection-q4_0.gguf` and [gemma3-12b-it](https://huggingface.co/gguf-org/ltx2-gguf/blob/main/gemma3-12b-it-q2_k.gguf) to `text_encoders`\n\nbtw, replace the `ltx2.3-22b-dev` or `-distill` with this universal checkpoint clip (see below) \n- pull `ltx2.3-22b-checkpoint_fp8_e4m3fn.safetensors` to `checkpoints`\n\nnote: you don't need any extra node for running `ltx2.3` under this setting; probably run it with beginner level gpu without problem, just wait slightly longer; you might need `protobuf` for rebuilding the tokenizer if you opt gemma3 gguf, simply install it with:\n```\n.\\python_embeded\\python.exe -s -m pip install protobuf\n```\n\n<p align=\"center\">\n  <video src=\"https://huggingface.co/gguf-org/ltx2.3-gguf/resolve/main/workflow-demo1.mp4\" controls width=\"100%\" style=\"max-width: 800px;\">\n    demo\n  </video>\n</p>",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "base_model:Lightricks/LTX-2.3",
    "base_model:quantized:Lightricks/LTX-2.3",
    "license:other",
    "region:us"
  ],
  "likes": 8,
  "downloads": 892,
  "gated": false,
  "private": false,
  "last_modified": "2026-03-08T11:11:58.000Z",
  "created_at": "2026-03-07T12:45:04.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "69ac1dd09d3713483a221bbd",
  "id": "gguf-org/ltx2.3-gguf",
  "modelId": "gguf-org/ltx2.3-gguf",
  "sha": "65ae5333340f1ae26ba63630497689c5617b3880",
  "createdAt": "2026-03-07T12:45:04.000Z",
  "lastModified": "2026-03-08T11:11:58.000Z",
  "author": "gguf-org",
  "downloads": 892,
  "likes": 8,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 14
}