mainguyenngoc/gemma3-4b-military-gemma3-4b_lr2e4_ep2_bs24x2_r64_a128_m7-gguf overview

{
  "metadata": {},
  "card_data": {
    "tags": [
      "gguf",
      "llama.cpp",
      "unsloth",
      "vision-language-model"
    ],
    "frontmatter": {
      "tags": [
        "gguf",
        "llama.cpp",
        "unsloth",
        "vision-language-model"
      ]
    },
    "hero_image_url": "https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png",
    "summary": "This model was finetuned and converted to GGUF format using Unsloth. **Example usage**:",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\ntags:\n- gguf\n- llama.cpp\n- unsloth\n- vision-language-model\n---\n\n# gemma3-4b-military-gemma3-4b_lr2e4_ep2_bs24x2_r64_a128_m7-GGUF : GGUF\n\nThis model was finetuned and converted to GGUF format using [Unsloth](https://github.com/unslothai/unsloth).\n\n**Example usage**:\n- For text only LLMs:    `./llama.cpp/llama-cli -hf mainguyenngoc/gemma3-4b-military-gemma3-4b_lr2e4_ep2_bs24x2_r64_a128_m7-GGUF --jinja`\n- For multimodal models: `./llama.cpp/llama-mtmd-cli -hf mainguyenngoc/gemma3-4b-military-gemma3-4b_lr2e4_ep2_bs24x2_r64_a128_m7-GGUF --jinja`\n\n## Available Model files:\n- `gemma-3-4b-it.Q4_K_M.gguf`\n- `gemma-3-4b-it.BF16-mmproj.gguf`\n\n## ⚠️ Ollama Note for Vision Models\n**Important:** Ollama currently does not support separate mmproj files for vision models.\n\nTo create an Ollama model from this vision model:\n1. Place the `Modelfile` in the same directory as the finetuned bf16 merged model\n3. Run: `ollama create model_name -f ./Modelfile`\n   (Replace `model_name` with your desired name)\n\nThis will create a unified bf16 model that Ollama can use.\n\n## Note\nThe model's BOS token behavior was adjusted for GGUF compatibility.\nThis was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth)\n[<img src=\"https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png\" width=\"200\"/>](https://github.com/unslothai/unsloth)\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "gemma3",
    "llama.cpp",
    "unsloth",
    "vision-language-model",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 113,
  "gated": false,
  "private": false,
  "last_modified": "2026-01-30T23:38:50.000Z",
  "created_at": "2026-01-30T23:38:00.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "697d40d88b0dd3ffab6cac22",
  "id": "mainguyenngoc/gemma3-4b-military-gemma3-4b_lr2e4_ep2_bs24x2_r64_a128_m7-GGUF",
  "modelId": "mainguyenngoc/gemma3-4b-military-gemma3-4b_lr2e4_ep2_bs24x2_r64_a128_m7-GGUF",
  "sha": "81a046573384fb99dc0470b8e5cdeb2d9b9fa64d",
  "createdAt": "2026-01-30T23:38:00.000Z",
  "lastModified": "2026-01-30T23:38:50.000Z",
  "author": "mainguyenngoc",
  "downloads": 113,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 6
}