aaryank/glm-4.6v-flash-gguf overview

{
  "metadata": {},
  "card_data": {
    "base_model": "zai-org/GLM-4.6V-Flash",
    "language": [
      "zh",
      "en"
    ],
    "library_name": "gguf",
    "license": "mit",
    "pipeline_tag": "image-text-to-text",
    "tags": [
      "zai",
      "glm-4",
      "vlm",
      "multimodal",
      "gguf",
      "moe"
    ],
    "frontmatter": {
      "base_model": "zai-org/GLM-4.6V-Flash",
      "language": [
        "zh",
        "en"
      ],
      "library_name": "gguf",
      "license": "mit",
      "pipeline_tag": "image-text-to-text",
      "tags": [
        "zai",
        "glm-4",
        "vlm",
        "multimodal",
        "gguf",
        "moe"
      ]
    },
    "hero_image_url": "",
    "summary": "This repository contains GGUF format quantizations of **zai-org/GLM-4.6V-Flash**.",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: zai-org/GLM-4.6V-Flash\nlanguage:\n- zh\n- en\nlibrary_name: gguf\nlicense: mit\npipeline_tag: image-text-to-text\ntags:\n- zai\n- glm-4\n- vlm\n- multimodal\n- gguf\n- moe\n---\n\n# GLM-4.6V-Flash-GGUF\n\nThis repository contains GGUF format quantizations of **[zai-org/GLM-4.6V-Flash](https://huggingface.co/zai-org/GLM-4.6V-Flash)**.\n\n## Model Introduction\n\n**GLM-4.6V-Flash** is a lightweight multimodal model (9B parameters) optimized for local deployment and low-latency applications, part of the GLM-V family. It features a 128k context window and achieves state-of-the-art performance in visual understanding among models of similar scale.\n\nKey features include:\n- **9B Parameters (MoE):** Optimized for efficiency.\n- **Native Multimodal Function Calling:** Can process images/screenshots directly as tool inputs.\n- **Interleaved Image-Text Generation:** Supports complex multimodal contexts.\n- **Document Understanding:** Processes up to 128K tokens of multi-document inputs.\n\n## Usage\n\n**Note:** This model uses the `Glm4vMoe` architecture. Please ensure you are using the latest version of [llama.cpp](https://github.com/ggerganov/llama.cpp) to ensure compatibility.\n\n### Example with llama.cpp\n\n```bash\n./llama-cli -m GLM-4.6V-Flash-Q4_K_M.gguf --mmproj GLM-4.6V-Flash-mmproj-model-f16.gguf -p \"Describe this image\" --image your_image.jpg",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "zai",
    "glm-4",
    "vlm",
    "multimodal",
    "moe",
    "image-text-to-text",
    "zh",
    "en",
    "base_model:zai-org/GLM-4.6V-Flash",
    "base_model:quantized:zai-org/GLM-4.6V-Flash",
    "license:mit",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 1,
  "downloads": 157,
  "gated": false,
  "private": false,
  "last_modified": "2025-12-08T17:23:47.000Z",
  "created_at": "2025-12-08T15:56:19.000Z",
  "pipeline_tag": "image-text-to-text",
  "library_name": "gguf"
}

{
  "_id": "6936f523005dc4acebfe28b3",
  "id": "AaryanK/GLM-4.6V-Flash-GGUF",
  "modelId": "AaryanK/GLM-4.6V-Flash-GGUF",
  "sha": "e7227cb937516ca2a52f73a75bc83ad3b66652c6",
  "createdAt": "2025-12-08T15:56:19.000Z",
  "lastModified": "2025-12-08T17:23:47.000Z",
  "author": "AaryanK",
  "downloads": 157,
  "likes": 1,
  "gated": false,
  "private": false,
  "pipeline_tag": "image-text-to-text",
  "library_name": "gguf",
  "siblings_count": 17
}