lovedheart/glm-4.5-air-gguf-iq1_m overview

{
  "metadata": {},
  "card_data": {
    "license": "mit",
    "base_model": [
      "zai-org/GLM-4.5-Air"
    ],
    "frontmatter": {
      "license": "mit",
      "base_model": [
        "zai-org/GLM-4.5-Air"
      ]
    },
    "hero_image_url": "",
    "summary": "Use unsloth BF16 GGUF to quantize IQ1_M/S. Blk.46 is not being used in llama.cpp therefore the weights of blk.46 are quantized to TQ1_0 to have minimum memory allocation. --- Added MXFP4 version: 1) MXFP4: Embedding, Output are kept with Q6_K. The attn layers use IQ4_XS. All ffn expert layers including shared experts are quantized to SOTA MXFP4. 2) MXFP4 Max: Embedding, Output and attn layers are kept with Q6_K. First layer uses full precision. The rest of ffn expert layers are quantized to SOTA MXFP4. The shared experts weights keep BF16.",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlicense: mit\nbase_model:\n- zai-org/GLM-4.5-Air\n---\n\nUse unsloth BF16 GGUF to quantize IQ1_M/S. Blk.46 is not being used in llama.cpp therefore the weights of blk.46 are quantized to TQ1_0 to have minimum memory allocation.\n\n---\nAdded MXFP4 version:\n1) MXFP4: Embedding, Output are kept with Q6_K. The attn layers use IQ4_XS. All ffn expert layers including shared experts are quantized to SOTA MXFP4.\n2) MXFP4 Max: Embedding, Output and attn layers are kept with Q6_K. First layer uses full precision. The rest of ffn expert layers are quantized to SOTA MXFP4. The shared experts weights keep BF16.",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "base_model:zai-org/GLM-4.5-Air",
    "base_model:quantized:zai-org/GLM-4.5-Air",
    "license:mit",
    "endpoints_compatible",
    "region:us",
    "imatrix",
    "conversational"
  ],
  "likes": 4,
  "downloads": 250,
  "gated": false,
  "private": false,
  "last_modified": "2025-08-26T05:57:05.000Z",
  "created_at": "2025-08-05T15:42:13.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "689226559416d9247e8b1d7f",
  "id": "lovedheart/GLM-4.5-Air-GGUF-IQ1_M",
  "modelId": "lovedheart/GLM-4.5-Air-GGUF-IQ1_M",
  "sha": "dad9c6ab5eec5f95ca3518489cd3a27e465c1acb",
  "createdAt": "2025-08-05T15:42:13.000Z",
  "lastModified": "2025-08-26T05:57:05.000Z",
  "author": "lovedheart",
  "downloads": 250,
  "likes": 4,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 42
}