richarderkhov/kenhktsui_-_llama3.2-3b-instruct-thinking-sft-merged-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png",
    "summary": "This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "Quantization made by Richard Erkhov.\n\n[Github](https://github.com/RichardErkhov)\n\n[Discord](https://discord.gg/pvy7H8DZMG)\n\n[Request more models](https://github.com/RichardErkhov/quant_request)\n\n\nllama3.2-3b-instruct-thinking-sft-merged - GGUF\n- Model creator: https://huggingface.co/kenhktsui/\n- Original model: https://huggingface.co/kenhktsui/llama3.2-3b-instruct-thinking-sft-merged/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [llama3.2-3b-instruct-thinking-sft-merged.Q2_K.gguf](https://huggingface.co/RichardErkhov/kenhktsui_-_llama3.2-3b-instruct-thinking-sft-merged-gguf/blob/main/llama3.2-3b-instruct-thinking-sft-merged.Q2_K.gguf) | Q2_K | 1.27GB |\n| [llama3.2-3b-instruct-thinking-sft-merged.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/kenhktsui_-_llama3.2-3b-instruct-thinking-sft-merged-gguf/blob/main/llama3.2-3b-instruct-thinking-sft-merged.IQ3_XS.gguf) | IQ3_XS | 1.38GB |\n| [llama3.2-3b-instruct-thinking-sft-merged.IQ3_S.gguf](https://huggingface.co/RichardErkhov/kenhktsui_-_llama3.2-3b-instruct-thinking-sft-merged-gguf/blob/main/llama3.2-3b-instruct-thinking-sft-merged.IQ3_S.gguf) | IQ3_S | 1.44GB |\n| [llama3.2-3b-instruct-thinking-sft-merged.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/kenhktsui_-_llama3.2-3b-instruct-thinking-sft-merged-gguf/blob/main/llama3.2-3b-instruct-thinking-sft-merged.Q3_K_S.gguf) | Q3_K_S | 1.44GB |\n| [llama3.2-3b-instruct-thinking-sft-merged.IQ3_M.gguf](https://huggingface.co/RichardErkhov/kenhktsui_-_llama3.2-3b-instruct-thinking-sft-merged-gguf/blob/main/llama3.2-3b-instruct-thinking-sft-merged.IQ3_M.gguf) | IQ3_M | 1.49GB |\n| [llama3.2-3b-instruct-thinking-sft-merged.Q3_K.gguf](https://huggingface.co/RichardErkhov/kenhktsui_-_llama3.2-3b-instruct-thinking-sft-merged-gguf/blob/main/llama3.2-3b-instruct-thinking-sft-merged.Q3_K.gguf) | Q3_K | 1.57GB |\n| [llama3.2-3b-instruct-thinking-sft-merged.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/kenhktsui_-_llama3.2-3b-instruct-thinking-sft-merged-gguf/blob/main/llama3.2-3b-instruct-thinking-sft-merged.Q3_K_M.gguf) | Q3_K_M | 1.57GB |\n| [llama3.2-3b-instruct-thinking-sft-merged.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/kenhktsui_-_llama3.2-3b-instruct-thinking-sft-merged-gguf/blob/main/llama3.2-3b-instruct-thinking-sft-merged.Q3_K_L.gguf) | Q3_K_L | 1.69GB |\n| [llama3.2-3b-instruct-thinking-sft-merged.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/kenhktsui_-_llama3.2-3b-instruct-thinking-sft-merged-gguf/blob/main/llama3.2-3b-instruct-thinking-sft-merged.IQ4_XS.gguf) | IQ4_XS | 1.71GB |\n| [llama3.2-3b-instruct-thinking-sft-merged.Q4_0.gguf](https://huggingface.co/RichardErkhov/kenhktsui_-_llama3.2-3b-instruct-thinking-sft-merged-gguf/blob/main/llama3.2-3b-instruct-thinking-sft-merged.Q4_0.gguf) | Q4_0 | 1.79GB |\n| [llama3.2-3b-instruct-thinking-sft-merged.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/kenhktsui_-_llama3.2-3b-instruct-thinking-sft-merged-gguf/blob/main/llama3.2-3b-instruct-thinking-sft-merged.IQ4_NL.gguf) | IQ4_NL | 1.79GB |\n| [llama3.2-3b-instruct-thinking-sft-merged.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/kenhktsui_-_llama3.2-3b-instruct-thinking-sft-merged-gguf/blob/main/llama3.2-3b-instruct-thinking-sft-merged.Q4_K_S.gguf) | Q4_K_S | 1.8GB |\n| [llama3.2-3b-instruct-thinking-sft-merged.Q4_K.gguf](https://huggingface.co/RichardErkhov/kenhktsui_-_llama3.2-3b-instruct-thinking-sft-merged-gguf/blob/main/llama3.2-3b-instruct-thinking-sft-merged.Q4_K.gguf) | Q4_K | 1.88GB |\n| [llama3.2-3b-instruct-thinking-sft-merged.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/kenhktsui_-_llama3.2-3b-instruct-thinking-sft-merged-gguf/blob/main/llama3.2-3b-instruct-thinking-sft-merged.Q4_K_M.gguf) | Q4_K_M | 1.88GB |\n| [llama3.2-3b-instruct-thinking-sft-merged.Q4_1.gguf](https://huggingface.co/RichardErkhov/kenhktsui_-_llama3.2-3b-instruct-thinking-sft-merged-gguf/blob/main/llama3.2-3b-instruct-thinking-sft-merged.Q4_1.gguf) | Q4_1 | 1.95GB |\n| [llama3.2-3b-instruct-thinking-sft-merged.Q5_0.gguf](https://huggingface.co/RichardErkhov/kenhktsui_-_llama3.2-3b-instruct-thinking-sft-merged-gguf/blob/main/llama3.2-3b-instruct-thinking-sft-merged.Q5_0.gguf) | Q5_0 | 2.11GB |\n| [llama3.2-3b-instruct-thinking-sft-merged.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/kenhktsui_-_llama3.2-3b-instruct-thinking-sft-merged-gguf/blob/main/llama3.2-3b-instruct-thinking-sft-merged.Q5_K_S.gguf) | Q5_K_S | 2.11GB |\n| [llama3.2-3b-instruct-thinking-sft-merged.Q5_K.gguf](https://huggingface.co/RichardErkhov/kenhktsui_-_llama3.2-3b-instruct-thinking-sft-merged-gguf/blob/main/llama3.2-3b-instruct-thinking-sft-merged.Q5_K.gguf) | Q5_K | 2.16GB |\n| [llama3.2-3b-instruct-thinking-sft-merged.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/kenhktsui_-_llama3.2-3b-instruct-thinking-sft-merged-gguf/blob/main/llama3.2-3b-instruct-thinking-sft-merged.Q5_K_M.gguf) | Q5_K_M | 2.16GB |\n| [llama3.2-3b-instruct-thinking-sft-merged.Q5_1.gguf](https://huggingface.co/RichardErkhov/kenhktsui_-_llama3.2-3b-instruct-thinking-sft-merged-gguf/blob/main/llama3.2-3b-instruct-thinking-sft-merged.Q5_1.gguf) | Q5_1 | 2.28GB |\n| [llama3.2-3b-instruct-thinking-sft-merged.Q6_K.gguf](https://huggingface.co/RichardErkhov/kenhktsui_-_llama3.2-3b-instruct-thinking-sft-merged-gguf/blob/main/llama3.2-3b-instruct-thinking-sft-merged.Q6_K.gguf) | Q6_K | 2.46GB |\n| [llama3.2-3b-instruct-thinking-sft-merged.Q8_0.gguf](https://huggingface.co/RichardErkhov/kenhktsui_-_llama3.2-3b-instruct-thinking-sft-merged-gguf/blob/main/llama3.2-3b-instruct-thinking-sft-merged.Q8_0.gguf) | Q8_0 | 3.19GB |\n\n\n\n\nOriginal model description:\n---\nbase_model: unsloth/llama-3.2-3b-instruct-bnb-4bit\ntags:\n- text-generation-inference\n- transformers\n- unsloth\n- llama\n- trl\n- sft\nlicense: apache-2.0\nlanguage:\n- en\n---\n\n# Uploaded  model\n\n- **Developed by:** kenhktsui\n- **License:** apache-2.0\n- **Finetuned from model :** unsloth/llama-3.2-3b-instruct-bnb-4bit\n\nThis llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.\n\n[<img src=\"https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png\" width=\"200\"/>](https://github.com/unslothai/unsloth)\n\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 949,
  "gated": false,
  "private": false,
  "last_modified": "2025-03-26T07:23:47.000Z",
  "created_at": "2025-03-26T06:22:26.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "67e39d225e0eef89cd209580",
  "id": "RichardErkhov/kenhktsui_-_llama3.2-3b-instruct-thinking-sft-merged-gguf",
  "modelId": "RichardErkhov/kenhktsui_-_llama3.2-3b-instruct-thinking-sft-merged-gguf",
  "sha": "7775c2020b7b70c2513a00a1c6259879d39b79a7",
  "createdAt": "2025-03-26T06:22:26.000Z",
  "lastModified": "2025-03-26T07:23:47.000Z",
  "author": "RichardErkhov",
  "downloads": 949,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}