richarderkhov/huggyllama_-_llama-30b-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "Quantization made by Richard Erkhov. Github Discord Request more models llama-30b - GGUF | Name | Quant method | Size | | ---- | ---- | ---- | | llama-30b.Q2_K.gguf | Q2_K | 11.22GB | | llama-30b.IQ3_XS.gguf | IQ3_XS | 12.4GB | | llama-30b.IQ3_S.gguf | IQ3_S | 13.1GB | | llama-30b.Q3_K_S.gguf | Q3_K_S | 13.1GB | | llama-30b.IQ3_M.gguf | IQ3_M | 13.86GB | | llama-30b.Q3_K.gguf | Q3_K | 14.69GB | | llama-30b.Q3_K_M.gguf | Q3_K_M | 14.69GB | | llama-30b.Q3_K_L.gguf | Q3_K_L | 16.09GB | | llama-30b.IQ4_XS.gguf | IQ4_XS | 16.28GB | | llama-30b.Q4_0.gguf | Q4_0 | 17.1GB | | llama-30b.IQ4_NL.gguf | IQ4_NL | 17.19GB | | llama-30b.Q4_K_S.gguf | Q4_K_S | 17.21GB | | llama-30b.Q4_K.gguf | Q4_K | 18.27GB | | llama-30b.Q4_K_M.gguf | Q4_K_M | 18.27GB | | llama-30b.Q4_1.gguf | Q4_1 | 18.98GB | | llama-30b.Q5_0.gguf | Q5_0 | 20.86GB | | llama-30b.Q5_K_S.gguf | Q5_K_S | 20.86GB | | llama-30b.Q5_K.gguf | Q5_K | 21.46GB | | llama-30b.Q5_K_M.gguf | Q5_K_M | 21.46GB | | llama-30b.Q5_1.gguf | Q5_1 | 22.74GB | | llama-30b.Q6_K.gguf | Q6_K | 24.85GB | | llama-30b.Q8_0.gguf | Q8_0 | 32.19GB | Original model description: --- license: other --- This contains the weights for the LLaMA-30b model. This model is under a non-commercial license (see the LICENSE file). You should only use this repository if you have been granted access to the model by filling out this form but either lost your copy of the weights or got some trouble converting them to the Transformers format.",
    "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\nllama-30b - GGUF\n- Model creator: https://huggingface.co/huggyllama/\n- Original model: https://huggingface.co/huggyllama/llama-30b/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [llama-30b.Q2_K.gguf](https://huggingface.co/RichardErkhov/huggyllama_-_llama-30b-gguf/blob/main/llama-30b.Q2_K.gguf) | Q2_K | 11.22GB |\n| [llama-30b.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/huggyllama_-_llama-30b-gguf/blob/main/llama-30b.IQ3_XS.gguf) | IQ3_XS | 12.4GB |\n| [llama-30b.IQ3_S.gguf](https://huggingface.co/RichardErkhov/huggyllama_-_llama-30b-gguf/blob/main/llama-30b.IQ3_S.gguf) | IQ3_S | 13.1GB |\n| [llama-30b.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/huggyllama_-_llama-30b-gguf/blob/main/llama-30b.Q3_K_S.gguf) | Q3_K_S | 13.1GB |\n| [llama-30b.IQ3_M.gguf](https://huggingface.co/RichardErkhov/huggyllama_-_llama-30b-gguf/blob/main/llama-30b.IQ3_M.gguf) | IQ3_M | 13.86GB |\n| [llama-30b.Q3_K.gguf](https://huggingface.co/RichardErkhov/huggyllama_-_llama-30b-gguf/blob/main/llama-30b.Q3_K.gguf) | Q3_K | 14.69GB |\n| [llama-30b.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/huggyllama_-_llama-30b-gguf/blob/main/llama-30b.Q3_K_M.gguf) | Q3_K_M | 14.69GB |\n| [llama-30b.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/huggyllama_-_llama-30b-gguf/blob/main/llama-30b.Q3_K_L.gguf) | Q3_K_L | 16.09GB |\n| [llama-30b.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/huggyllama_-_llama-30b-gguf/blob/main/llama-30b.IQ4_XS.gguf) | IQ4_XS | 16.28GB |\n| [llama-30b.Q4_0.gguf](https://huggingface.co/RichardErkhov/huggyllama_-_llama-30b-gguf/blob/main/llama-30b.Q4_0.gguf) | Q4_0 | 17.1GB |\n| [llama-30b.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/huggyllama_-_llama-30b-gguf/blob/main/llama-30b.IQ4_NL.gguf) | IQ4_NL | 17.19GB |\n| [llama-30b.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/huggyllama_-_llama-30b-gguf/blob/main/llama-30b.Q4_K_S.gguf) | Q4_K_S | 17.21GB |\n| [llama-30b.Q4_K.gguf](https://huggingface.co/RichardErkhov/huggyllama_-_llama-30b-gguf/blob/main/llama-30b.Q4_K.gguf) | Q4_K | 18.27GB |\n| [llama-30b.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/huggyllama_-_llama-30b-gguf/blob/main/llama-30b.Q4_K_M.gguf) | Q4_K_M | 18.27GB |\n| [llama-30b.Q4_1.gguf](https://huggingface.co/RichardErkhov/huggyllama_-_llama-30b-gguf/blob/main/llama-30b.Q4_1.gguf) | Q4_1 | 18.98GB |\n| [llama-30b.Q5_0.gguf](https://huggingface.co/RichardErkhov/huggyllama_-_llama-30b-gguf/blob/main/llama-30b.Q5_0.gguf) | Q5_0 | 20.86GB |\n| [llama-30b.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/huggyllama_-_llama-30b-gguf/blob/main/llama-30b.Q5_K_S.gguf) | Q5_K_S | 20.86GB |\n| [llama-30b.Q5_K.gguf](https://huggingface.co/RichardErkhov/huggyllama_-_llama-30b-gguf/blob/main/llama-30b.Q5_K.gguf) | Q5_K | 21.46GB |\n| [llama-30b.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/huggyllama_-_llama-30b-gguf/blob/main/llama-30b.Q5_K_M.gguf) | Q5_K_M | 21.46GB |\n| [llama-30b.Q5_1.gguf](https://huggingface.co/RichardErkhov/huggyllama_-_llama-30b-gguf/blob/main/llama-30b.Q5_1.gguf) | Q5_1 | 22.74GB |\n| [llama-30b.Q6_K.gguf](https://huggingface.co/RichardErkhov/huggyllama_-_llama-30b-gguf/blob/main/llama-30b.Q6_K.gguf) | Q6_K | 24.85GB |\n| [llama-30b.Q8_0.gguf](https://huggingface.co/RichardErkhov/huggyllama_-_llama-30b-gguf/blob/main/llama-30b.Q8_0.gguf) | Q8_0 | 32.19GB |\n\n\n\n\nOriginal model description:\n---\nlicense: other\n---\n\nThis contains the weights for the LLaMA-30b model. This model is under a non-commercial license (see the LICENSE file).\nYou should only use this repository if you have been granted access to the model by filling out [this form](https://docs.google.com/forms/d/e/1FAIpQLSfqNECQnMkycAp2jP4Z9TFX0cGR4uf7b_fBxjY_OjhJILlKGA/viewform?usp=send_form) but either lost your copy of the weights or got some trouble converting them to the Transformers format.\n\n\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us"
  ],
  "likes": 0,
  "downloads": 483,
  "gated": false,
  "private": false,
  "last_modified": "2024-07-26T15:03:52.000Z",
  "created_at": "2024-07-25T18:01:26.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "66a292f63ea52a727b0fa2f1",
  "id": "RichardErkhov/huggyllama_-_llama-30b-gguf",
  "modelId": "RichardErkhov/huggyllama_-_llama-30b-gguf",
  "sha": "33154cbc215a34898b2e473911b02b525e8a267b",
  "createdAt": "2024-07-25T18:01:26.000Z",
  "lastModified": "2024-07-26T15:03:52.000Z",
  "author": "RichardErkhov",
  "downloads": 483,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}