Model Intelligence Sheet
mradermacher/magnum-v4-27b-i1-gguf overview
About weighted/imatrix quants of https://huggingface.co/anthracite-org/magnum-v4-27b static quants are available at https://huggingface.co/mradermacher/magnum-v4-27b-GGUF
Downloads
445
Likes
2
Pipeline
—
Library
transformers
Visibility
Public
Access
Open
Repository Files & Downloads
21 files detected
Direct downloads for all repository files
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| magnum-v4-27b.i1-IQ1_M.gguf | GGUF | IQ1_M | 6.23 GB | Download |
| magnum-v4-27b.i1-IQ1_S.gguf | GGUF | IQ1_S | 5.71 GB | Download |
| magnum-v4-27b.i1-IQ2_M.gguf | GGUF | IQ2_M | 8.75 GB | Download |
| magnum-v4-27b.i1-IQ2_S.gguf | GGUF | IQ2_S | 8.06 GB | Download |
| magnum-v4-27b.i1-IQ2_XS.gguf | GGUF | IQ2_XS | 7.82 GB | Download |
| magnum-v4-27b.i1-IQ2_XXS.gguf | GGUF | IQ2_XXS | 7.10 GB | Download |
| magnum-v4-27b.i1-IQ3_M.gguf | GGUF | IQ3_M | 11.60 GB | Download |
| magnum-v4-27b.i1-IQ3_S.gguf | GGUF | IQ3_S | 11.33 GB | Download |
| magnum-v4-27b.i1-IQ3_XS.gguf | GGUF | IQ3_XS | 10.76 GB | Download |
| magnum-v4-27b.i1-IQ3_XXS.gguf | GGUF | IQ3_XXS | 10.01 GB | Download |
| magnum-v4-27b.i1-IQ4_XS.gguf | GGUF | IQ4_XS | 13.80 GB | Download |
| magnum-v4-27b.i1-Q2_K.gguf | GGUF | Q2_K | 9.73 GB | Download |
| magnum-v4-27b.i1-Q3_K_L.gguf | GGUF | Q3_K_L | 13.52 GB | Download |
| magnum-v4-27b.i1-Q3_K_M.gguf | GGUF | Q3_K_M | 12.50 GB | Download |
| magnum-v4-27b.i1-Q3_K_S.gguf | GGUF | Q3_K_S | 11.33 GB | Download |
| magnum-v4-27b.i1-Q4_0.gguf | GGUF | — | 14.60 GB | Download |
| magnum-v4-27b.i1-Q4_K_M.gguf | GGUF | Q4_K_M | 15.50 GB | Download |
| magnum-v4-27b.i1-Q4_K_S.gguf | GGUF | Q4_K_S | 14.66 GB | Download |
| magnum-v4-27b.i1-Q5_K_M.gguf | GGUF | Q5_K_M | 18.08 GB | Download |
| magnum-v4-27b.i1-Q5_K_S.gguf | GGUF | Q5_K_S | 17.59 GB | Download |
| magnum-v4-27b.i1-Q6_K.gguf | GGUF | Q6_K | 20.81 GB | Download |
Model Details Live
Metadata Inspector
Normalized metadata (stored in metadata_json)
{
"metadata": {},
"card_data": {
"base_model": "anthracite-org/magnum-v4-27b",
"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-v4-27b",
"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-v4-27b static quants are available at https://huggingface.co/mradermacher/magnum-v4-27b-GGUF",
"quick_links": [],
"benchmark_table_html": "",
"readme_markdown": "---\nbase_model: anthracite-org/magnum-v4-27b\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-v4-27b\n\n<!-- provided-files -->\nstatic quants are available at https://huggingface.co/mradermacher/magnum-v4-27b-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-v4-27b-i1-GGUF/resolve/main/magnum-v4-27b.i1-IQ1_S.gguf) | i1-IQ1_S | 6.2 | for the desperate |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-27b-i1-GGUF/resolve/main/magnum-v4-27b.i1-IQ1_M.gguf) | i1-IQ1_M | 6.8 | mostly desperate |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-27b-i1-GGUF/resolve/main/magnum-v4-27b.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 7.7 | |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-27b-i1-GGUF/resolve/main/magnum-v4-27b.i1-IQ2_XS.gguf) | i1-IQ2_XS | 8.5 | |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-27b-i1-GGUF/resolve/main/magnum-v4-27b.i1-IQ2_S.gguf) | i1-IQ2_S | 8.8 | |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-27b-i1-GGUF/resolve/main/magnum-v4-27b.i1-IQ2_M.gguf) | i1-IQ2_M | 9.5 | |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-27b-i1-GGUF/resolve/main/magnum-v4-27b.i1-Q2_K.gguf) | i1-Q2_K | 10.5 | IQ3_XXS probably better |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-27b-i1-GGUF/resolve/main/magnum-v4-27b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 10.9 | lower quality |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-27b-i1-GGUF/resolve/main/magnum-v4-27b.i1-IQ3_XS.gguf) | i1-IQ3_XS | 11.7 | |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-27b-i1-GGUF/resolve/main/magnum-v4-27b.i1-IQ3_S.gguf) | i1-IQ3_S | 12.3 | beats Q3_K* |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-27b-i1-GGUF/resolve/main/magnum-v4-27b.i1-Q3_K_S.gguf) | i1-Q3_K_S | 12.3 | IQ3_XS probably better |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-27b-i1-GGUF/resolve/main/magnum-v4-27b.i1-IQ3_M.gguf) | i1-IQ3_M | 12.6 | |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-27b-i1-GGUF/resolve/main/magnum-v4-27b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 13.5 | IQ3_S probably better |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-27b-i1-GGUF/resolve/main/magnum-v4-27b.i1-Q3_K_L.gguf) | i1-Q3_K_L | 14.6 | IQ3_M probably better |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-27b-i1-GGUF/resolve/main/magnum-v4-27b.i1-IQ4_XS.gguf) | i1-IQ4_XS | 14.9 | |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-27b-i1-GGUF/resolve/main/magnum-v4-27b.i1-Q4_0.gguf) | i1-Q4_0 | 15.8 | fast, low quality |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-27b-i1-GGUF/resolve/main/magnum-v4-27b.i1-Q4_K_S.gguf) | i1-Q4_K_S | 15.8 | optimal size/speed/quality |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-27b-i1-GGUF/resolve/main/magnum-v4-27b.i1-Q4_K_M.gguf) | i1-Q4_K_M | 16.7 | fast, recommended |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-27b-i1-GGUF/resolve/main/magnum-v4-27b.i1-Q5_K_S.gguf) | i1-Q5_K_S | 19.0 | |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-27b-i1-GGUF/resolve/main/magnum-v4-27b.i1-Q5_K_M.gguf) | i1-Q5_K_M | 19.5 | |\n| [GGUF](https://huggingface.co/mradermacher/magnum-v4-27b-i1-GGUF/resolve/main/magnum-v4-27b.i1-Q6_K.gguf) | i1-Q6_K | 22.4 | practically like static Q6_K |\n\nHere is a handy graph by ikawrakow comparing some lower-quality quant\ntypes (lower is better):\n\n\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-v4-27b",
"base_model:quantized:anthracite-org/magnum-v4-27b",
"license:gemma",
"endpoints_compatible",
"region:us",
"imatrix",
"conversational"
],
"likes": 2,
"downloads": 445,
"gated": false,
"private": false,
"last_modified": "2024-11-26T13:51:00.000Z",
"created_at": "2024-10-21T01:26:42.000Z",
"pipeline_tag": "",
"library_name": "transformers"
}
Source payload excerpt (from Hugging Face API)
{
"_id": "6715add2e22b5aceb930be38",
"id": "mradermacher/magnum-v4-27b-i1-GGUF",
"modelId": "mradermacher/magnum-v4-27b-i1-GGUF",
"sha": "928b997af62df601cfc61045e8c43379fe590656",
"createdAt": "2024-10-21T01:26:42.000Z",
"lastModified": "2024-11-26T13:51:00.000Z",
"author": "mradermacher",
"downloads": 445,
"likes": 2,
"gated": false,
"private": false,
"pipeline_tag": "",
"library_name": "transformers",
"siblings_count": 24
}