second-state/nemotron-mini-4b-instruct-gguf overview

{
  "metadata": {},
  "card_data": {
    "base_model": "nvidia/Nemotron-Mini-4B-Instruct",
    "license": "other",
    "license_name": "nvidia-community-model-license",
    "inference": false,
    "model_creator": "nvidia",
    "model_name": "Nemotron-Mini-4B-Instruct",
    "quantized_by": "Second State Inc.",
    "library_name": "nemo",
    "frontmatter": {
      "base_model": "nvidia/Nemotron-Mini-4B-Instruct",
      "license": "other",
      "license_name": "nvidia-community-model-license",
      "inference": "false",
      "model_creator": "nvidia",
      "model_name": "Nemotron-Mini-4B-Instruct",
      "quantized_by": "Second State Inc.",
      "library_name": "nemo"
    },
    "hero_image_url": "https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg",
    "summary": "",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: nvidia/Nemotron-Mini-4B-Instruct\nlicense: other\nlicense_name: nvidia-community-model-license\ninference: false\nmodel_creator: nvidia\nmodel_name: Nemotron-Mini-4B-Instruct\nquantized_by: Second State Inc.\nlibrary_name: nemo\n---\n\n<!-- header start -->\n<!-- 200823 -->\n<div style=\"width: auto; margin-left: auto; margin-right: auto\">\n<img src=\"https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg\" style=\"width: 100%; min-width: 400px; display: block; margin: auto;\">\n</div>\n<hr style=\"margin-top: 1.0em; margin-bottom: 1.0em;\">\n<!-- header end -->\n\n# Nemotron-Mini-4B-Instruct-GGUF\n\n## Original Model\n\n[nvidia/Nemotron-Mini-4B-Instruct](https://huggingface.co/nvidia/Nemotron-Mini-4B-Instruct)\n\n## Run with LlamaEdge\n\n- LlamaEdge version: coming soon\n\n<!-- - LlamaEdge version: [v0.14.2](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.14.2) and above -->\n\n- Prompt template\n\n  - Prompt type: `nemotron-chat`\n\n  - Prompt string\n\n    ```text\n    <extra_id_0>System\n    {system_message}\n    <extra_id_1>User\n    {user_message_1}<extra_id_1>Assistant\n    {assistant_message_1}\n    <extra_id_1>User\n    {user_message_2}<extra_id_1>Assistant\n    {assistant_message_2}\n    <extra_id_1>User\n    {user_message_3}\n    <extra_id_1>Assistant\\n\n    ```\n\n    - Tool use\n\n      ```text\n      <extra_id_0>System\n      {system_message}\n      <tool> {tool_1} </tool>\n      <tool> {tool_2} </tool>\n    \n    \n      <extra_id_1>User\n      {user_message_1}<extra_id_1>Assistant\n      <toolcall> {tool_call_message} </toolcall>\n      <extra_id_1>Tool\n      {tool_result_message}\n      <extra_id_1>Assistant\\n\n      ```\n\n- Context size: `4096`\n\n- Run as LlamaEdge service\n\n  ```bash\n  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Nemotron-Mini-4B-Instruct-Q5_K_M.gguf \\\n    llama-api-server.wasm \\\n    --prompt-template nemotron-chat \\\n    --ctx-size 4096 \\\n    --model-name Nemotron-Mini-4B-Instruct\n  ```\n\n  - Tool use\n\n    ```bash\n    wasmedge --dir .:. --nn-preload default:GGML:AUTO:Nemotron-Mini-4B-Instruct-Q5_K_M.gguf \\\n      llama-api-server.wasm \\\n      --prompt-template nemotron-tool \\\n      --ctx-size 4096 \\\n      --model-name Nemotron-Mini-4B-Instruct\n    ```\n\n- Run as LlamaEdge command app\n\n  ```bash\n  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Nemotron-Mini-4B-Instruct-Q5_K_M.gguf \\\n    llama-chat.wasm \\\n    --prompt-template nemotron-chat \\\n    --ctx-size 4096\n  ```\n\n## Quantized GGUF Models\n\n| Name | Quant method | Bits | Size | Use case |\n| ---- | ---- | ---- | ---- | ----- |\n| [Nemotron-Mini-4B-Instruct-Q2_K.gguf](https://huggingface.co/second-state/Nemotron-Mini-4B-Instruct-GGUF/blob/main/Nemotron-Mini-4B-Instruct-Q2_K.gguf)     | Q2_K   | 2 | 3.35 GB| smallest, significant quality loss - not recommended for most purposes |\n| [Nemotron-Mini-4B-Instruct-Q3_K_L.gguf](https://huggingface.co/second-state/Nemotron-Mini-4B-Instruct-GGUF/blob/main/Nemotron-Mini-4B-Instruct-Q3_K_L.gguf) | Q3_K_L | 3 | 4.69 GB| small, substantial quality loss |\n| [Nemotron-Mini-4B-Instruct-Q3_K_M.gguf](https://huggingface.co/second-state/Nemotron-Mini-4B-Instruct-GGUF/blob/main/Nemotron-Mini-4B-Instruct-Q3_K_M.gguf) | Q3_K_M | 3 | 4.32 GB| very small, high quality loss |\n| [Nemotron-Mini-4B-Instruct-Q3_K_S.gguf](https://huggingface.co/second-state/Nemotron-Mini-4B-Instruct-GGUF/blob/main/Nemotron-Mini-4B-Instruct-Q3_K_S.gguf) | Q3_K_S | 3 | 3.90 GB| very small, high quality loss |\n| [Nemotron-Mini-4B-Instruct-Q4_0.gguf](https://huggingface.co/second-state/Nemotron-Mini-4B-Instruct-GGUF/blob/main/Nemotron-Mini-4B-Instruct-Q4_0.gguf)     | Q4_0   | 4 | 5.04 GB| legacy; small, very high quality loss - prefer using Q3_K_M |\n| [Nemotron-Mini-4B-Instruct-Q4_K_M.gguf](https://huggingface.co/second-state/Nemotron-Mini-4B-Instruct-GGUF/blob/main/Nemotron-Mini-4B-Instruct-Q4_K_M.gguf) | Q4_K_M | 4 | 5.33 GB| medium, balanced quality - recommended |\n| [Nemotron-Mini-4B-Instruct-Q4_K_S.gguf](https://huggingface.co/second-state/Nemotron-Mini-4B-Instruct-GGUF/blob/main/Nemotron-Mini-4B-Instruct-Q4_K_S.gguf) | Q4_K_S | 4 | 5.07 GB| small, greater quality loss |\n| [Nemotron-Mini-4B-Instruct-Q5_0.gguf](https://huggingface.co/second-state/Nemotron-Mini-4B-Instruct-GGUF/blob/main/Nemotron-Mini-4B-Instruct-Q5_0.gguf)     | Q5_0   | 5 | 6.11 GB| legacy; medium, balanced quality - prefer using Q4_K_M |\n| [Nemotron-Mini-4B-Instruct-Q5_K_M.gguf](https://huggingface.co/second-state/Nemotron-Mini-4B-Instruct-GGUF/blob/main/Nemotron-Mini-4B-Instruct-Q5_K_M.gguf) | Q5_K_M | 5 | 6.26 GB| large, very low quality loss - recommended |\n| [Nemotron-Mini-4B-Instruct-Q5_K_S.gguf](https://huggingface.co/second-state/Nemotron-Mini-4B-Instruct-GGUF/blob/main/Nemotron-Mini-4B-Instruct-Q5_K_S.gguf) | Q5_K_S | 5 | 6.11 GB| large, low quality loss - recommended |\n| [Nemotron-Mini-4B-Instruct-Q6_K.gguf](https://huggingface.co/second-state/Nemotron-Mini-4B-Instruct-GGUF/blob/main/Nemotron-Mini-4B-Instruct-Q6_K.gguf)     | Q6_K   | 6 | 7.25 GB| very large, extremely low quality loss |\n| [Nemotron-Mini-4B-Instruct-Q8_0.gguf](https://huggingface.co/second-state/Nemotron-Mini-4B-Instruct-GGUF/blob/main/Nemotron-Mini-4B-Instruct-Q8_0.gguf)     | Q8_0   | 8 | 9.38 GB| very large, extremely low quality loss - not recommended |\n| [Nemotron-Mini-4B-Instruct-f16.gguf](https://huggingface.co/second-state/Nemotron-Mini-4B-Instruct-GGUF/blob/main/Nemotron-Mini-4B-Instruct-f16.gguf)       | f16   | 16 | 17.7 GB| |\n\n*Quantized with llama.cpp b3751*",
    "related_quantizations": []
  },
  "tags": [
    "nemo",
    "gguf",
    "base_model:nvidia/Nemotron-Mini-4B-Instruct",
    "base_model:quantized:nvidia/Nemotron-Mini-4B-Instruct",
    "license:other",
    "region:us",
    "conversational"
  ],
  "likes": 1,
  "downloads": 234,
  "gated": false,
  "private": false,
  "last_modified": "2025-08-29T03:03:36.000Z",
  "created_at": "2024-09-15T12:00:19.000Z",
  "pipeline_tag": "",
  "library_name": "nemo"
}

{
  "_id": "66e6cc537723058632b2a98b",
  "id": "second-state/Nemotron-Mini-4B-Instruct-GGUF",
  "modelId": "second-state/Nemotron-Mini-4B-Instruct-GGUF",
  "sha": "216fa6d1abe430989f0242f6b29eb77f35f0fc28",
  "createdAt": "2024-09-15T12:00:19.000Z",
  "lastModified": "2025-08-29T03:03:36.000Z",
  "author": "second-state",
  "downloads": 234,
  "likes": 1,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "nemo",
  "siblings_count": 29
}