bigatuna/nouscoder-14b-gguf overview

{
  "metadata": {},
  "card_data": {
    "base_model": "NousResearch/NousCoder-14B",
    "library_name": "llama.cpp",
    "tags": [
      "gguf",
      "quantized",
      "coding",
      "nouscoder"
    ],
    "license": "apache-2.0",
    "frontmatter": {
      "base_model": "NousResearch/NousCoder-14B",
      "library_name": "llama.cpp",
      "tags": [
        "gguf",
        "quantized",
        "coding",
        "nouscoder"
      ],
      "license": "apache-2.0"
    },
    "hero_image_url": "",
    "summary": "GGUF quantizations of NousResearch/NousCoder-14B for use with llama.cpp, Ollama, LM Studio, and other GGUF-compatible inference engines.",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: NousResearch/NousCoder-14B\nlibrary_name: llama.cpp\ntags:\n  - gguf\n  - quantized\n  - coding\n  - nouscoder\nlicense: apache-2.0\n---\n\n# NousCoder-14B GGUF\n\nGGUF quantizations of [NousResearch/NousCoder-14B](https://huggingface.co/NousResearch/NousCoder-14B) for use with llama.cpp, Ollama, LM Studio, and other GGUF-compatible inference engines.\n\n## Credits\n\nAll credit goes to **[NousResearch](https://huggingface.co/NousResearch)** for training and releasing the original NousCoder-14B model. This repo only provides quantized GGUF versions for easier local inference.\n\n## Available Quants\n\n| Filename | Quant | Size | Description |\n|----------|-------|------|-------------|\n| `nouscoder-14b-q4_k_m.gguf` | Q4_K_M | 8.4 GB | Good balance of quality and size |\n| `nouscoder-14b-q3_k_m.gguf` | Q3_K_M | 6.9 GB | Lower memory, good quality |\n| `nouscoder-14b-q3_k_s.gguf` | Q3_K_S | 6.2 GB | Smallest, for constrained environments |\n\n## Usage\n\n### llama.cpp\n```bash\n./llama-cli -m nouscoder-14b-q4_k_m.gguf -p \"def fibonacci(n):\"\n```\n\n### Ollama\n```bash\nollama run hf.co/bigatuna/NousCoder-14B-GGUF:Q4_K_M\n```\n\n## Original Model\n\n- **Model**: [NousResearch/NousCoder-14B](https://huggingface.co/NousResearch/NousCoder-14B)\n- **License**: Apache 2.0\n- **Parameters**: 14B\n",
    "related_quantizations": []
  },
  "tags": [
    "llama.cpp",
    "gguf",
    "quantized",
    "coding",
    "nouscoder",
    "base_model:NousResearch/NousCoder-14B",
    "base_model:quantized:NousResearch/NousCoder-14B",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 9,
  "downloads": 123,
  "gated": false,
  "private": false,
  "last_modified": "2026-01-08T04:13:04.000Z",
  "created_at": "2026-01-07T06:04:25.000Z",
  "pipeline_tag": "",
  "library_name": "llama.cpp"
}

{
  "_id": "695df769ce33bbec610d8c97",
  "id": "bigatuna/NousCoder-14B-GGUF",
  "modelId": "bigatuna/NousCoder-14B-GGUF",
  "sha": "6b13de91c24ce4092ccc8d4ab8f746bd4615e1c5",
  "createdAt": "2026-01-07T06:04:25.000Z",
  "lastModified": "2026-01-08T04:13:04.000Z",
  "author": "bigatuna",
  "downloads": 123,
  "likes": 9,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "llama.cpp",
  "siblings_count": 5
}