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

mradermacher/magnum-v4-9b-i1-gguf overview

About weighted/imatrix quants of https://huggingface.co/anthracite-org/magnum-v4-9b static quants are available at https://huggingface.co/mradermacher/magnum-v4-9b-GGUF

transformersggufchatendataset:anthracite-org/c2_logs_16k_llama_v1.1dataset:NewEden/Claude-Instruct-5Kdataset:anthracite-org/kalo-opus-instruct-22k-no-refusaldataset:Epiculous/SynthRP-Gens-v1.1-Filtered-n-Cleaneddataset:lodrick-the-lafted/kalo-opus-instruct-3k-filtereddataset:anthracite-org/nopm_claude_writing_fixeddataset:Epiculous/Synthstruct-Gens-v1.1-Filtered-n-Cleaneddataset:anthracite-org/kalo_opus_misc_240827dataset:anthracite-org/kalo_misc_part2base_model:anthracite-org/magnum-v4-9bbase_model:quantized:anthracite-org/magnum-v4-9blicense:gemmaendpoints_compatibleregion:usimatrixconversational
mradermacher/magnum-v4-9b-i1-gguf visual
Downloads
2,288
Likes
3
Pipeline
Library
transformers
Visibility
Public
Access
Open

Repository Files & Downloads

24 files detected
Direct downloads for all repository files
FileTypeQuantizationSizeLink
magnum-v4-9b.i1-IQ1_M.gguf GGUF IQ1_M 2.37 GB Download
magnum-v4-9b.i1-IQ1_S.gguf GGUF IQ1_S 2.22 GB Download
magnum-v4-9b.i1-IQ2_M.gguf GGUF IQ2_M 3.20 GB Download
magnum-v4-9b.i1-IQ2_S.gguf GGUF IQ2_S 2.99 GB Download
magnum-v4-9b.i1-IQ2_XS.gguf GGUF IQ2_XS 2.86 GB Download
magnum-v4-9b.i1-IQ2_XXS.gguf GGUF IQ2_XXS 2.63 GB Download
magnum-v4-9b.i1-IQ3_M.gguf GGUF IQ3_M 4.19 GB Download
magnum-v4-9b.i1-IQ3_S.gguf GGUF IQ3_S 4.04 GB Download
magnum-v4-9b.i1-IQ3_XS.gguf GGUF IQ3_XS 3.86 GB Download
magnum-v4-9b.i1-IQ3_XXS.gguf GGUF IQ3_XXS 3.54 GB Download
magnum-v4-9b.i1-IQ4_XS.gguf GGUF IQ4_XS 4.83 GB Download
magnum-v4-9b.i1-Q2_K.gguf GGUF Q2_K 3.54 GB Download
magnum-v4-9b.i1-Q3_K_L.gguf GGUF Q3_K_L 4.78 GB Download
magnum-v4-9b.i1-Q3_K_M.gguf GGUF Q3_K_M 4.43 GB Download
magnum-v4-9b.i1-Q3_K_S.gguf GGUF Q3_K_S 4.04 GB Download
magnum-v4-9b.i1-Q4_0.gguf GGUF 5.08 GB Download
magnum-v4-9b.i1-Q4_0_4_4.gguf GGUF 5.07 GB Download
magnum-v4-9b.i1-Q4_0_4_8.gguf GGUF 5.07 GB Download
magnum-v4-9b.i1-Q4_0_8_8.gguf GGUF 5.07 GB Download
magnum-v4-9b.i1-Q4_K_M.gguf GGUF Q4_K_M 5.37 GB Download
magnum-v4-9b.i1-Q4_K_S.gguf GGUF Q4_K_S 5.10 GB Download
magnum-v4-9b.i1-Q5_K_M.gguf GGUF Q5_K_M 6.19 GB Download
magnum-v4-9b.i1-Q5_K_S.gguf GGUF Q5_K_S 6.04 GB Download
magnum-v4-9b.i1-Q6_K.gguf GGUF Q6_K 7.07 GB Download

Model Details Live

Model Slug
mradermacher/magnum-v4-9b-i1-gguf
Author
mradermacher
Pipeline Task
Library
transformers
Created
2024-10-20
Last Modified
2024-11-26
Gated
No
Private
No
HF SHA
672ff3f1ec80a615ae4ae2d75302a50f896d234a
License
gemma
Language
en
Base Model
anthracite-org/magnum-v4-9b

Metadata Inspector

Normalized metadata (stored in metadata_json)
{
  "metadata": {},
  "card_data": {
    "base_model": "anthracite-org/magnum-v4-9b",
    "datasets": [
      "anthracite-org/c2_logs_16k_llama_v1.1",
      "NewEden/Claude-Instruct-5K",
      "anthracite-org/kalo-opus-instruct-22k-no-refusal",
      "Epiculous/SynthRP-Gens-v1.1-Filtered-n-Cleaned",
      "lodrick-the-lafted/kalo-opus-instruct-3k-filtered",
      "anthracite-org/nopm_claude_writing_fixed",
      "Epiculous/Synthstruct-Gens-v1.1-Filtered-n-Cleaned",
      "anthracite-org/kalo_opus_misc_240827",
      "anthracite-org/kalo_misc_part2"
    ],
    "language": [
      "en"
    ],
    "library_name": "transformers",
    "license": "gemma",
    "quantized_by": "mradermacher",
    "tags": [
      "chat"
    ],
    "frontmatter": {
      "base_model": "anthracite-org/magnum-v4-9b",
      "datasets": [
        "anthracite-org/c2_logs_16k_llama_v1.1",
        "NewEden/Claude-Instruct-5K",
        "anthracite-org/kalo-opus-instruct-22k-no-refusal",
        "Epiculous/SynthRP-Gens-v1.1-Filtered-n-Cleaned",
        "lodrick-the-lafted/kalo-opus-instruct-3k-filtered",
        "anthracite-org/nopm_claude_writing_fixed",
        "Epiculous/Synthstruct-Gens-v1.1-Filtered-n-Cleaned",
        "anthracite-org/kalo_opus_misc_240827",
        "anthracite-org/kalo_misc_part2"
      ],
      "language": [
        "en"
      ],
      "library_name": "transformers",
      "license": "gemma",
      "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-v4-9b  static quants are available at https://huggingface.co/mradermacher/magnum-v4-9b-GGUF",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: anthracite-org/magnum-v4-9b\ndatasets:\n- anthracite-org/c2_logs_16k_llama_v1.1\n- NewEden/Claude-Instruct-5K\n- anthracite-org/kalo-opus-instruct-22k-no-refusal\n- Epiculous/SynthRP-Gens-v1.1-Filtered-n-Cleaned\n- lodrick-the-lafted/kalo-opus-instruct-3k-filtered\n- anthracite-org/nopm_claude_writing_fixed\n- Epiculous/Synthstruct-Gens-v1.1-Filtered-n-Cleaned\n- anthracite-org/kalo_opus_misc_240827\n- anthracite-org/kalo_misc_part2\nlanguage:\n- en\nlibrary_name: transformers\nlicense: gemma\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-v4-9b\n\n<!-- provided-files -->\nstatic quants are available at https://huggingface.co/mradermacher/magnum-v4-9b-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-v4-9b-i1-GGUF/resolve/main/magnum-v4-9b.i1-IQ1_S.gguf) | i1-IQ1_S | 2.5 | for the desperate |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-9b-i1-GGUF/resolve/main/magnum-v4-9b.i1-IQ1_M.gguf) | i1-IQ1_M | 2.6 | mostly desperate |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-9b-i1-GGUF/resolve/main/magnum-v4-9b.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.9 |  |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-9b-i1-GGUF/resolve/main/magnum-v4-9b.i1-IQ2_XS.gguf) | i1-IQ2_XS | 3.2 |  |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-9b-i1-GGUF/resolve/main/magnum-v4-9b.i1-IQ2_S.gguf) | i1-IQ2_S | 3.3 |  |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-9b-i1-GGUF/resolve/main/magnum-v4-9b.i1-IQ2_M.gguf) | i1-IQ2_M | 3.5 |  |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-9b-i1-GGUF/resolve/main/magnum-v4-9b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.9 | lower quality |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-9b-i1-GGUF/resolve/main/magnum-v4-9b.i1-Q2_K.gguf) | i1-Q2_K | 3.9 | IQ3_XXS probably better |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-9b-i1-GGUF/resolve/main/magnum-v4-9b.i1-IQ3_XS.gguf) | i1-IQ3_XS | 4.2 |  |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-9b-i1-GGUF/resolve/main/magnum-v4-9b.i1-IQ3_S.gguf) | i1-IQ3_S | 4.4 | beats Q3_K* |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-9b-i1-GGUF/resolve/main/magnum-v4-9b.i1-Q3_K_S.gguf) | i1-Q3_K_S | 4.4 | IQ3_XS probably better |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-9b-i1-GGUF/resolve/main/magnum-v4-9b.i1-IQ3_M.gguf) | i1-IQ3_M | 4.6 |  |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-9b-i1-GGUF/resolve/main/magnum-v4-9b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.9 | IQ3_S probably better |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-9b-i1-GGUF/resolve/main/magnum-v4-9b.i1-Q3_K_L.gguf) | i1-Q3_K_L | 5.2 | IQ3_M probably better |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-9b-i1-GGUF/resolve/main/magnum-v4-9b.i1-IQ4_XS.gguf) | i1-IQ4_XS | 5.3 |  |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-9b-i1-GGUF/resolve/main/magnum-v4-9b.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 5.5 | fast on arm, low quality |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-9b-i1-GGUF/resolve/main/magnum-v4-9b.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 5.5 | fast on arm+i8mm, low quality |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-9b-i1-GGUF/resolve/main/magnum-v4-9b.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 5.5 | fast on arm+sve, low quality |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-9b-i1-GGUF/resolve/main/magnum-v4-9b.i1-Q4_0.gguf) | i1-Q4_0 | 5.6 | fast, low quality |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-9b-i1-GGUF/resolve/main/magnum-v4-9b.i1-Q4_K_S.gguf) | i1-Q4_K_S | 5.6 | optimal size/speed/quality |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-9b-i1-GGUF/resolve/main/magnum-v4-9b.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.9 | fast, recommended |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-9b-i1-GGUF/resolve/main/magnum-v4-9b.i1-Q5_K_S.gguf) | i1-Q5_K_S | 6.6 |  |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-9b-i1-GGUF/resolve/main/magnum-v4-9b.i1-Q5_K_M.gguf) | i1-Q5_K_M | 6.7 |  |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-9b-i1-GGUF/resolve/main/magnum-v4-9b.i1-Q6_K.gguf) | i1-Q6_K | 7.7 | 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_16k_llama_v1.1",
    "dataset:NewEden/Claude-Instruct-5K",
    "dataset:anthracite-org/kalo-opus-instruct-22k-no-refusal",
    "dataset:Epiculous/SynthRP-Gens-v1.1-Filtered-n-Cleaned",
    "dataset:lodrick-the-lafted/kalo-opus-instruct-3k-filtered",
    "dataset:anthracite-org/nopm_claude_writing_fixed",
    "dataset:Epiculous/Synthstruct-Gens-v1.1-Filtered-n-Cleaned",
    "dataset:anthracite-org/kalo_opus_misc_240827",
    "dataset:anthracite-org/kalo_misc_part2",
    "base_model:anthracite-org/magnum-v4-9b",
    "base_model:quantized:anthracite-org/magnum-v4-9b",
    "license:gemma",
    "endpoints_compatible",
    "region:us",
    "imatrix",
    "conversational"
  ],
  "likes": 3,
  "downloads": 2288,
  "gated": false,
  "private": false,
  "last_modified": "2024-11-26T13:51:20.000Z",
  "created_at": "2024-10-20T15:15:43.000Z",
  "pipeline_tag": "",
  "library_name": "transformers"
}
Source payload excerpt (from Hugging Face API)
{
  "_id": "67151e9f9d55d647b7fc9c81",
  "id": "mradermacher/magnum-v4-9b-i1-GGUF",
  "modelId": "mradermacher/magnum-v4-9b-i1-GGUF",
  "sha": "672ff3f1ec80a615ae4ae2d75302a50f896d234a",
  "createdAt": "2024-10-20T15:15:43.000Z",
  "lastModified": "2024-11-26T13:51:20.000Z",
  "author": "mradermacher",
  "downloads": 2288,
  "likes": 3,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "transformers",
  "siblings_count": 27
}