GraySoft
Projects Models About FAQ Contact Download guIDE →
Model Intelligence Sheet

mradermacher/magnum-v4-12b-i1-gguf overview

About weighted/imatrix quants of https://huggingface.co/anthracite-org/magnum-v4-12b static quants are available at https://huggingface.co/mradermacher/magnum-v4-12b-GGUF

transformersggufchatendataset:anthracite-org/c2_logs_32k_llama3_qwen2_v1.2_no_systemdataset:anthracite-org/kalo-opus-instruct-22k-no-refusal-no-systemdataset:anthracite-org/kalo-opus-instruct-3k-filtered-no-systemdataset:anthracite-org/nopm_claude_writing_fixeddataset:anthracite-org/kalo_opus_misc_240827_no_systemdataset:anthracite-org/kalo_misc_part2_no_systembase_model:anthracite-org/magnum-v4-12bbase_model:quantized:anthracite-org/magnum-v4-12blicense:apache-2.0endpoints_compatibleregion:usimatrixconversational
mradermacher/magnum-v4-12b-i1-gguf visual
Downloads
370
Likes
8
Pipeline
Library
transformers
Visibility
Public
Access
Open

Repository Files & Downloads

21 files detected
Direct downloads for all repository files
FileTypeQuantizationSizeLink
magnum-v4-12b.i1-IQ1_M.gguf GGUF IQ1_M 3.00 GB Download
magnum-v4-12b.i1-IQ1_S.gguf GGUF IQ1_S 2.79 GB Download
magnum-v4-12b.i1-IQ2_M.gguf GGUF IQ2_M 4.13 GB Download
magnum-v4-12b.i1-IQ2_S.gguf GGUF IQ2_S 3.85 GB Download
magnum-v4-12b.i1-IQ2_XS.gguf GGUF IQ2_XS 3.65 GB Download
magnum-v4-12b.i1-IQ2_XXS.gguf GGUF IQ2_XXS 3.35 GB Download
magnum-v4-12b.i1-IQ3_M.gguf GGUF IQ3_M 5.33 GB Download
magnum-v4-12b.i1-IQ3_S.gguf GGUF IQ3_S 5.18 GB Download
magnum-v4-12b.i1-IQ3_XS.gguf GGUF IQ3_XS 4.94 GB Download
magnum-v4-12b.i1-IQ3_XXS.gguf GGUF IQ3_XXS 4.61 GB Download
magnum-v4-12b.i1-IQ4_XS.gguf GGUF IQ4_XS 6.28 GB Download
magnum-v4-12b.i1-Q2_K.gguf GGUF Q2_K 4.46 GB Download
magnum-v4-12b.i1-Q3_K_L.gguf GGUF Q3_K_L 6.11 GB Download
magnum-v4-12b.i1-Q3_K_M.gguf GGUF Q3_K_M 5.67 GB Download
magnum-v4-12b.i1-Q3_K_S.gguf GGUF Q3_K_S 5.15 GB Download
magnum-v4-12b.i1-Q4_0.gguf GGUF 6.61 GB Download
magnum-v4-12b.i1-Q4_K_M.gguf GGUF Q4_K_M 6.96 GB Download
magnum-v4-12b.i1-Q4_K_S.gguf GGUF Q4_K_S 6.63 GB Download
magnum-v4-12b.i1-Q5_K_M.gguf GGUF Q5_K_M 8.13 GB Download
magnum-v4-12b.i1-Q5_K_S.gguf GGUF Q5_K_S 7.93 GB Download
magnum-v4-12b.i1-Q6_K.gguf GGUF Q6_K 9.37 GB Download

Model Details Live

Model Slug
mradermacher/magnum-v4-12b-i1-gguf
Author
mradermacher
Pipeline Task
Library
transformers
Created
2024-10-20
Last Modified
2024-11-26
Gated
No
Private
No
HF SHA
d918a9e8a92b85716885fa8e6f0506079b3671ae
License
apache-2.0
Language
en
Base Model
anthracite-org/magnum-v4-12b

Metadata Inspector

Normalized metadata (stored in metadata_json)
{
  "metadata": {},
  "card_data": {
    "base_model": "anthracite-org/magnum-v4-12b",
    "datasets": [
      "anthracite-org/c2_logs_32k_llama3_qwen2_v1.2_no_system",
      "anthracite-org/kalo-opus-instruct-22k-no-refusal-no-system",
      "anthracite-org/kalo-opus-instruct-3k-filtered-no-system",
      "anthracite-org/nopm_claude_writing_fixed",
      "anthracite-org/kalo_opus_misc_240827_no_system",
      "anthracite-org/kalo_misc_part2_no_system"
    ],
    "language": [
      "en"
    ],
    "library_name": "transformers",
    "license": "apache-2.0",
    "license_name": "mrl",
    "quantized_by": "mradermacher",
    "tags": [
      "chat"
    ],
    "frontmatter": {
      "base_model": "anthracite-org/magnum-v4-12b",
      "datasets": [
        "anthracite-org/c2_logs_32k_llama3_qwen2_v1.2_no_system",
        "anthracite-org/kalo-opus-instruct-22k-no-refusal-no-system",
        "anthracite-org/kalo-opus-instruct-3k-filtered-no-system",
        "anthracite-org/nopm_claude_writing_fixed",
        "anthracite-org/kalo_opus_misc_240827_no_system",
        "anthracite-org/kalo_misc_part2_no_system"
      ],
      "language": [
        "en"
      ],
      "library_name": "transformers",
      "license": "apache-2.0",
      "license_name": "mrl",
      "quantized_by": "mradermacher",
      "tags": [
        "chat"
      ]
    },
    "hero_image_url": "https://www.nethype.de/huggingface_embed/quantpplgraph.png",
    "summary": "## About      weighted/imatrix quants of https://huggingface.co/anthracite-org/magnum-v4-12b  static quants are available at https://huggingface.co/mradermacher/magnum-v4-12b-GGUF",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: anthracite-org/magnum-v4-12b\ndatasets:\n- anthracite-org/c2_logs_32k_llama3_qwen2_v1.2_no_system\n- anthracite-org/kalo-opus-instruct-22k-no-refusal-no-system\n- anthracite-org/kalo-opus-instruct-3k-filtered-no-system\n- anthracite-org/nopm_claude_writing_fixed\n- anthracite-org/kalo_opus_misc_240827_no_system\n- anthracite-org/kalo_misc_part2_no_system\nlanguage:\n- en\nlibrary_name: transformers\nlicense: apache-2.0\nlicense_name: mrl\nquantized_by: mradermacher\ntags:\n- chat\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/anthracite-org/magnum-v4-12b\n\n<!-- provided-files -->\nstatic quants are available at https://huggingface.co/mradermacher/magnum-v4-12b-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/magnum-v4-12b-i1-GGUF/resolve/main/magnum-v4-12b.i1-IQ1_S.gguf) | i1-IQ1_S | 3.1 | for the desperate |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-12b-i1-GGUF/resolve/main/magnum-v4-12b.i1-IQ1_M.gguf) | i1-IQ1_M | 3.3 | mostly desperate |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-12b-i1-GGUF/resolve/main/magnum-v4-12b.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.7 |  |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-12b-i1-GGUF/resolve/main/magnum-v4-12b.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.0 |  |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-12b-i1-GGUF/resolve/main/magnum-v4-12b.i1-IQ2_S.gguf) | i1-IQ2_S | 4.2 |  |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-12b-i1-GGUF/resolve/main/magnum-v4-12b.i1-IQ2_M.gguf) | i1-IQ2_M | 4.5 |  |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-12b-i1-GGUF/resolve/main/magnum-v4-12b.i1-Q2_K.gguf) | i1-Q2_K | 4.9 | IQ3_XXS probably better |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-12b-i1-GGUF/resolve/main/magnum-v4-12b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 5.0 | lower quality |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-12b-i1-GGUF/resolve/main/magnum-v4-12b.i1-IQ3_XS.gguf) | i1-IQ3_XS | 5.4 |  |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-12b-i1-GGUF/resolve/main/magnum-v4-12b.i1-Q3_K_S.gguf) | i1-Q3_K_S | 5.6 | IQ3_XS probably better |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-12b-i1-GGUF/resolve/main/magnum-v4-12b.i1-IQ3_S.gguf) | i1-IQ3_S | 5.7 | beats Q3_K* |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-12b-i1-GGUF/resolve/main/magnum-v4-12b.i1-IQ3_M.gguf) | i1-IQ3_M | 5.8 |  |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-12b-i1-GGUF/resolve/main/magnum-v4-12b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 6.2 | IQ3_S probably better |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-12b-i1-GGUF/resolve/main/magnum-v4-12b.i1-Q3_K_L.gguf) | i1-Q3_K_L | 6.7 | IQ3_M probably better |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-12b-i1-GGUF/resolve/main/magnum-v4-12b.i1-IQ4_XS.gguf) | i1-IQ4_XS | 6.8 |  |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-12b-i1-GGUF/resolve/main/magnum-v4-12b.i1-Q4_0.gguf) | i1-Q4_0 | 7.2 | fast, low quality |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-12b-i1-GGUF/resolve/main/magnum-v4-12b.i1-Q4_K_S.gguf) | i1-Q4_K_S | 7.2 | optimal size/speed/quality |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-12b-i1-GGUF/resolve/main/magnum-v4-12b.i1-Q4_K_M.gguf) | i1-Q4_K_M | 7.6 | fast, recommended |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-12b-i1-GGUF/resolve/main/magnum-v4-12b.i1-Q5_K_S.gguf) | i1-Q5_K_S | 8.6 |  |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-12b-i1-GGUF/resolve/main/magnum-v4-12b.i1-Q5_K_M.gguf) | i1-Q5_K_M | 8.8 |  |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-12b-i1-GGUF/resolve/main/magnum-v4-12b.i1-Q6_K.gguf) | i1-Q6_K | 10.2 | 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",
    "chat",
    "en",
    "dataset:anthracite-org/c2_logs_32k_llama3_qwen2_v1.2_no_system",
    "dataset:anthracite-org/kalo-opus-instruct-22k-no-refusal-no-system",
    "dataset:anthracite-org/kalo-opus-instruct-3k-filtered-no-system",
    "dataset:anthracite-org/nopm_claude_writing_fixed",
    "dataset:anthracite-org/kalo_opus_misc_240827_no_system",
    "dataset:anthracite-org/kalo_misc_part2_no_system",
    "base_model:anthracite-org/magnum-v4-12b",
    "base_model:quantized:anthracite-org/magnum-v4-12b",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us",
    "imatrix",
    "conversational"
  ],
  "likes": 8,
  "downloads": 370,
  "gated": false,
  "private": false,
  "last_modified": "2024-11-26T13:51:12.000Z",
  "created_at": "2024-10-20T15:26:27.000Z",
  "pipeline_tag": "",
  "library_name": "transformers"
}
Source payload excerpt (from Hugging Face API)
{
  "_id": "671521239ad69db7193f4b1c",
  "id": "mradermacher/magnum-v4-12b-i1-GGUF",
  "modelId": "mradermacher/magnum-v4-12b-i1-GGUF",
  "sha": "d918a9e8a92b85716885fa8e6f0506079b3671ae",
  "createdAt": "2024-10-20T15:26:27.000Z",
  "lastModified": "2024-11-26T13:51:12.000Z",
  "author": "mradermacher",
  "downloads": 370,
  "likes": 8,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "transformers",
  "siblings_count": 24
}