mradermacher/medgemma-4b-it-i1-gguf overview

{
  "metadata": {},
  "card_data": {
    "base_model": "google/medgemma-4b-it",
    "extra_gated_button_content": "Acknowledge license",
    "extra_gated_heading": "Access MedGemma on Hugging Face",
    "extra_gated_prompt": "To access MedGemma on Hugging Face, you're required to review and agree to [Health AI Developer Foundation's terms of use](https://developers.google.com/health-ai-developer-foundations/terms). To do this, please ensure you're logged in to Hugging Face and click below. Requests are processed immediately.",
    "language": [
      "en"
    ],
    "library_name": "transformers",
    "license": "other",
    "license_link": "https://developers.google.com/health-ai-developer-foundations/terms",
    "license_name": "health-ai-developer-foundations",
    "mradermacher": {
      "readme_rev": 1
    },
    "quantized_by": "mradermacher",
    "tags": [
      "medical",
      "radiology",
      "clinical-reasoning",
      "dermatology",
      "pathology",
      "ophthalmology",
      "chest-x-ray"
    ],
    "frontmatter": {
      "base_model": "google/medgemma-4b-it",
      "extra_gated_button_content": "Acknowledge license",
      "extra_gated_heading": "Access MedGemma on Hugging Face",
      "extra_gated_prompt": "To access MedGemma on Hugging Face, you're required to review",
      "language": [
        "en"
      ],
      "library_name": "transformers",
      "license": "other",
      "license_link": "https://developers.google.com/health-ai-developer-foundations/terms",
      "license_name": "health-ai-developer-foundations",
      "mradermacher": [],
      "quantized_by": "mradermacher",
      "tags": [
        "medical",
        "radiology",
        "clinical-reasoning",
        "dermatology",
        "pathology",
        "ophthalmology",
        "chest-x-ray"
      ]
    },
    "hero_image_url": "https://www.nethype.de/huggingface_embed/quantpplgraph.png",
    "summary": "## About      weighted/imatrix quants of https://huggingface.co/google/medgemma-4b-it  ***For a convenient overview and download list, visit our model page for this model.*** static quants are available at https://huggingface.co/mradermacher/medgemma-4b-it-GGUF **This is a vision model - mmproj files (if any) will be in the static repository.**",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: google/medgemma-4b-it\nextra_gated_button_content: Acknowledge license\nextra_gated_heading: Access MedGemma on Hugging Face\nextra_gated_prompt: To access MedGemma on Hugging Face, you're required to review\n  and agree to [Health AI Developer Foundation's terms of use](https://developers.google.com/health-ai-developer-foundations/terms).\n  To do this, please ensure you're logged in to Hugging Face and click below. Requests\n  are processed immediately.\nlanguage:\n- en\nlibrary_name: transformers\nlicense: other\nlicense_link: https://developers.google.com/health-ai-developer-foundations/terms\nlicense_name: health-ai-developer-foundations\nmradermacher:\n  readme_rev: 1\nquantized_by: mradermacher\ntags:\n- medical\n- radiology\n- clinical-reasoning\n- dermatology\n- pathology\n- ophthalmology\n- chest-x-ray\n---\n## About\n\n<!-- ### quantize_version: 2 -->\n<!-- ### output_tensor_quantised: 1 -->\n<!-- ### convert_type: hf -->\n<!-- ### vocab_type:  -->\n<!-- ### tags: nicoboss -->\nweighted/imatrix quants of https://huggingface.co/google/medgemma-4b-it\n\n<!-- provided-files -->\n\n***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#medgemma-4b-it-i1-GGUF).***\n\nstatic quants are available at https://huggingface.co/mradermacher/medgemma-4b-it-GGUF\n\n**This is a vision model - mmproj files (if any) will be in the [static repository](https://huggingface.co/mradermacher/medgemma-4b-it-GGUF).**\n## Usage\n\nIf you are unsure how to use GGUF files, refer to one of [TheBloke's\nREADMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for\nmore details, including on how to concatenate multi-part files.\n\n## Provided Quants\n\n(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)\n\n| Link | Type | Size/GB | Notes |\n|:-----|:-----|--------:|:------|\n| [GGUF](https://huggingface.co/mradermacher/medgemma-4b-it-i1-GGUF/resolve/main/medgemma-4b-it.i1-IQ1_S.gguf) | i1-IQ1_S | 1.2 | for the desperate |\n| [GGUF](https://huggingface.co/mradermacher/medgemma-4b-it-i1-GGUF/resolve/main/medgemma-4b-it.i1-IQ1_M.gguf) | i1-IQ1_M | 1.3 | mostly desperate |\n| [GGUF](https://huggingface.co/mradermacher/medgemma-4b-it-i1-GGUF/resolve/main/medgemma-4b-it.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.4 |  |\n| [GGUF](https://huggingface.co/mradermacher/medgemma-4b-it-i1-GGUF/resolve/main/medgemma-4b-it.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.5 |  |\n| [GGUF](https://huggingface.co/mradermacher/medgemma-4b-it-i1-GGUF/resolve/main/medgemma-4b-it.i1-IQ2_S.gguf) | i1-IQ2_S | 1.5 |  |\n| [GGUF](https://huggingface.co/mradermacher/medgemma-4b-it-i1-GGUF/resolve/main/medgemma-4b-it.i1-IQ2_M.gguf) | i1-IQ2_M | 1.6 |  |\n| [GGUF](https://huggingface.co/mradermacher/medgemma-4b-it-i1-GGUF/resolve/main/medgemma-4b-it.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.7 | very low quality |\n| [GGUF](https://huggingface.co/mradermacher/medgemma-4b-it-i1-GGUF/resolve/main/medgemma-4b-it.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.8 | lower quality |\n| [GGUF](https://huggingface.co/mradermacher/medgemma-4b-it-i1-GGUF/resolve/main/medgemma-4b-it.i1-Q2_K.gguf) | i1-Q2_K | 1.8 | IQ3_XXS probably better |\n| [GGUF](https://huggingface.co/mradermacher/medgemma-4b-it-i1-GGUF/resolve/main/medgemma-4b-it.i1-IQ3_XS.gguf) | i1-IQ3_XS | 2.0 |  |\n| [GGUF](https://huggingface.co/mradermacher/medgemma-4b-it-i1-GGUF/resolve/main/medgemma-4b-it.i1-IQ3_S.gguf) | i1-IQ3_S | 2.0 | beats Q3_K* |\n| [GGUF](https://huggingface.co/mradermacher/medgemma-4b-it-i1-GGUF/resolve/main/medgemma-4b-it.i1-Q3_K_S.gguf) | i1-Q3_K_S | 2.0 | IQ3_XS probably better |\n| [GGUF](https://huggingface.co/mradermacher/medgemma-4b-it-i1-GGUF/resolve/main/medgemma-4b-it.i1-IQ3_M.gguf) | i1-IQ3_M | 2.1 |  |\n| [GGUF](https://huggingface.co/mradermacher/medgemma-4b-it-i1-GGUF/resolve/main/medgemma-4b-it.i1-Q3_K_M.gguf) | i1-Q3_K_M | 2.2 | IQ3_S probably better |\n| [GGUF](https://huggingface.co/mradermacher/medgemma-4b-it-i1-GGUF/resolve/main/medgemma-4b-it.i1-Q3_K_L.gguf) | i1-Q3_K_L | 2.3 | IQ3_M probably better |\n| [GGUF](https://huggingface.co/mradermacher/medgemma-4b-it-i1-GGUF/resolve/main/medgemma-4b-it.i1-IQ4_XS.gguf) | i1-IQ4_XS | 2.4 |  |\n| [GGUF](https://huggingface.co/mradermacher/medgemma-4b-it-i1-GGUF/resolve/main/medgemma-4b-it.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.5 | prefer IQ4_XS |\n| [GGUF](https://huggingface.co/mradermacher/medgemma-4b-it-i1-GGUF/resolve/main/medgemma-4b-it.i1-Q4_0.gguf) | i1-Q4_0 | 2.5 | fast, low quality |\n| [GGUF](https://huggingface.co/mradermacher/medgemma-4b-it-i1-GGUF/resolve/main/medgemma-4b-it.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.5 | optimal size/speed/quality |\n| [GGUF](https://huggingface.co/mradermacher/medgemma-4b-it-i1-GGUF/resolve/main/medgemma-4b-it.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.6 | fast, recommended |\n| [GGUF](https://huggingface.co/mradermacher/medgemma-4b-it-i1-GGUF/resolve/main/medgemma-4b-it.i1-Q4_1.gguf) | i1-Q4_1 | 2.7 |  |\n| [GGUF](https://huggingface.co/mradermacher/medgemma-4b-it-i1-GGUF/resolve/main/medgemma-4b-it.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.9 |  |\n| [GGUF](https://huggingface.co/mradermacher/medgemma-4b-it-i1-GGUF/resolve/main/medgemma-4b-it.i1-Q5_K_M.gguf) | i1-Q5_K_M | 2.9 |  |\n| [GGUF](https://huggingface.co/mradermacher/medgemma-4b-it-i1-GGUF/resolve/main/medgemma-4b-it.i1-Q6_K.gguf) | i1-Q6_K | 3.3 | practically like static Q6_K |\n\nHere is a handy graph by ikawrakow comparing some lower-quality quant\ntypes (lower is better):\n\n![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)\n\nAnd here are Artefact2's thoughts on the matter:\nhttps://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9\n\n## FAQ / Model Request\n\nSee https://huggingface.co/mradermacher/model_requests for some answers to\nquestions you might have and/or if you want some other model quantized.\n\n## Thanks\n\nI thank my company, [nethype GmbH](https://www.nethype.de/), for letting\nme use its servers and providing upgrades to my workstation to enable\nthis work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.\n\n<!-- end -->\n",
    "related_quantizations": []
  },
  "tags": [
    "transformers",
    "gguf",
    "medical",
    "radiology",
    "clinical-reasoning",
    "dermatology",
    "pathology",
    "ophthalmology",
    "chest-x-ray",
    "en",
    "base_model:google/medgemma-4b-it",
    "base_model:quantized:google/medgemma-4b-it",
    "license:other",
    "endpoints_compatible",
    "region:us",
    "imatrix",
    "conversational"
  ],
  "likes": 1,
  "downloads": 89,
  "gated": false,
  "private": false,
  "last_modified": "2025-07-11T02:10:51.000Z",
  "created_at": "2025-05-24T20:06:53.000Z",
  "pipeline_tag": "",
  "library_name": "transformers"
}

{
  "_id": "683226dd5602502c8d4227bc",
  "id": "mradermacher/medgemma-4b-it-i1-GGUF",
  "modelId": "mradermacher/medgemma-4b-it-i1-GGUF",
  "sha": "e72473b68139c8f77427dd21270eff3b2b80c1f9",
  "createdAt": "2025-05-24T20:06:53.000Z",
  "lastModified": "2025-07-11T02:10:51.000Z",
  "author": "mradermacher",
  "downloads": 89,
  "likes": 1,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "transformers",
  "siblings_count": 27
}