mradermacher/aegolius-acadicus-34b-v3-i1-gguf Q5_K_M GGUF - Free GGUF Download is indexed on GraySoft with repository links, GGUF quant files, and Hugging Face metadata. This page helps you pick a local model for guIDE or other runtimes. See related models in the same shard below.
Model Intelligence Sheet
mradermacher/aegolius-acadicus-34b-v3-i1-gguf overview
About weighted/imatrix quants of https://huggingface.co/ibivibiv/aegolius-acadicus-34b-v3 static quants are available at https://huggingface.co/mradermacher/aegolius-acadicus-34b-v3-GGUF
Downloads
90
Likes
0
Pipeline
—
Library
transformers
Visibility
Public
Access
Open
Repository Files & Downloads
21 files detected
Direct downloads for all repository files
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| aegolius-acadicus-34b-v3.i1-IQ1_M.gguf | GGUF | IQ1_M | 7.50 GB | Download |
| aegolius-acadicus-34b-v3.i1-IQ1_S.gguf | GGUF | IQ1_S | 6.78 GB | Download |
| aegolius-acadicus-34b-v3.i1-IQ2_M.gguf | GGUF | IQ2_M | 10.86 GB | Download |
| aegolius-acadicus-34b-v3.i1-IQ2_S.gguf | GGUF | IQ2_S | 9.90 GB | Download |
| aegolius-acadicus-34b-v3.i1-IQ2_XS.gguf | GGUF | IQ2_XS | 9.68 GB | Download |
| aegolius-acadicus-34b-v3.i1-IQ2_XXS.gguf | GGUF | IQ2_XXS | 8.70 GB | Download |
| aegolius-acadicus-34b-v3.i1-IQ3_M.gguf | GGUF | IQ3_M | 14.49 GB | Download |
| aegolius-acadicus-34b-v3.i1-IQ3_S.gguf | GGUF | IQ3_S | 14.25 GB | Download |
| aegolius-acadicus-34b-v3.i1-IQ3_XS.gguf | GGUF | IQ3_XS | 13.48 GB | Download |
| aegolius-acadicus-34b-v3.i1-IQ3_XXS.gguf | GGUF | IQ3_XXS | 12.68 GB | Download |
| aegolius-acadicus-34b-v3.i1-IQ4_XS.gguf | GGUF | IQ4_XS | 17.59 GB | Download |
| aegolius-acadicus-34b-v3.i1-Q2_K.gguf | GGUF | Q2_K | 12.04 GB | Download |
| aegolius-acadicus-34b-v3.i1-Q3_K_L.gguf | GGUF | Q3_K_L | 17.10 GB | Download |
| aegolius-acadicus-34b-v3.i1-Q3_K_M.gguf | GGUF | Q3_K_M | 15.79 GB | Download |
| aegolius-acadicus-34b-v3.i1-Q3_K_S.gguf | GGUF | Q3_K_S | 14.23 GB | Download |
| aegolius-acadicus-34b-v3.i1-Q4_0.gguf | GGUF | — | 18.68 GB | Download |
| aegolius-acadicus-34b-v3.i1-Q4_K_M.gguf | GGUF | Q4_K_M | 19.96 GB | Download |
| aegolius-acadicus-34b-v3.i1-Q4_K_S.gguf | GGUF | Q4_K_S | 18.76 GB | Download |
| aegolius-acadicus-34b-v3.i1-Q5_K_M.gguf | GGUF | Q5_K_M | 23.41 GB | Download |
| aegolius-acadicus-34b-v3.i1-Q5_K_S.gguf | GGUF | Q5_K_S | 22.70 GB | Download |
| aegolius-acadicus-34b-v3.i1-Q6_K.gguf | GGUF | Q6_K | 27.07 GB | Download |
Model Details Live
Metadata Inspector
Normalized metadata (stored in metadata_json)
{
"metadata": {},
"card_data": {
"base_model": "ibivibiv/aegolius-acadicus-34b-v3",
"language": [
"en"
],
"library_name": "transformers",
"license": "apache-2.0",
"quantized_by": "mradermacher",
"tags": [
"moe"
],
"frontmatter": {
"base_model": "ibivibiv/aegolius-acadicus-34b-v3",
"language": [
"en"
],
"library_name": "transformers",
"license": "apache-2.0",
"quantized_by": "mradermacher",
"tags": [
"moe"
]
},
"hero_image_url": "https://www.nethype.de/huggingface_embed/quantpplgraph.png",
"summary": "## About weighted/imatrix quants of https://huggingface.co/ibivibiv/aegolius-acadicus-34b-v3 static quants are available at https://huggingface.co/mradermacher/aegolius-acadicus-34b-v3-GGUF",
"quick_links": [],
"benchmark_table_html": "",
"readme_markdown": "---\nbase_model: ibivibiv/aegolius-acadicus-34b-v3\nlanguage:\n- en\nlibrary_name: transformers\nlicense: apache-2.0\nquantized_by: mradermacher\ntags:\n- moe\n---\n## About\n\n<!-- ### quantize_version: 1 -->\n<!-- ### output_tensor_quantised: 1 -->\n<!-- ### convert_type: -->\n<!-- ### vocab_type: -->\nweighted/imatrix quants of https://huggingface.co/ibivibiv/aegolius-acadicus-34b-v3\n\n<!-- provided-files -->\nstatic quants are available at https://huggingface.co/mradermacher/aegolius-acadicus-34b-v3-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/aegolius-acadicus-34b-v3-i1-GGUF/resolve/main/aegolius-acadicus-34b-v3.i1-IQ1_S.gguf) | i1-IQ1_S | 7.4 | for the desperate |\n| [GGUF](https://huggingface.co/mradermacher/aegolius-acadicus-34b-v3-i1-GGUF/resolve/main/aegolius-acadicus-34b-v3.i1-IQ1_M.gguf) | i1-IQ1_M | 8.2 | mostly desperate |\n| [GGUF](https://huggingface.co/mradermacher/aegolius-acadicus-34b-v3-i1-GGUF/resolve/main/aegolius-acadicus-34b-v3.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 9.4 | |\n| [GGUF](https://huggingface.co/mradermacher/aegolius-acadicus-34b-v3-i1-GGUF/resolve/main/aegolius-acadicus-34b-v3.i1-IQ2_XS.gguf) | i1-IQ2_XS | 10.5 | |\n| [GGUF](https://huggingface.co/mradermacher/aegolius-acadicus-34b-v3-i1-GGUF/resolve/main/aegolius-acadicus-34b-v3.i1-IQ2_S.gguf) | i1-IQ2_S | 10.7 | |\n| [GGUF](https://huggingface.co/mradermacher/aegolius-acadicus-34b-v3-i1-GGUF/resolve/main/aegolius-acadicus-34b-v3.i1-IQ2_M.gguf) | i1-IQ2_M | 11.8 | |\n| [GGUF](https://huggingface.co/mradermacher/aegolius-acadicus-34b-v3-i1-GGUF/resolve/main/aegolius-acadicus-34b-v3.i1-Q2_K.gguf) | i1-Q2_K | 13.0 | IQ3_XXS probably better |\n| [GGUF](https://huggingface.co/mradermacher/aegolius-acadicus-34b-v3-i1-GGUF/resolve/main/aegolius-acadicus-34b-v3.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 13.7 | lower quality |\n| [GGUF](https://huggingface.co/mradermacher/aegolius-acadicus-34b-v3-i1-GGUF/resolve/main/aegolius-acadicus-34b-v3.i1-IQ3_XS.gguf) | i1-IQ3_XS | 14.6 | |\n| [GGUF](https://huggingface.co/mradermacher/aegolius-acadicus-34b-v3-i1-GGUF/resolve/main/aegolius-acadicus-34b-v3.i1-Q3_K_S.gguf) | i1-Q3_K_S | 15.4 | IQ3_XS probably better |\n| [GGUF](https://huggingface.co/mradermacher/aegolius-acadicus-34b-v3-i1-GGUF/resolve/main/aegolius-acadicus-34b-v3.i1-IQ3_S.gguf) | i1-IQ3_S | 15.4 | beats Q3_K* |\n| [GGUF](https://huggingface.co/mradermacher/aegolius-acadicus-34b-v3-i1-GGUF/resolve/main/aegolius-acadicus-34b-v3.i1-IQ3_M.gguf) | i1-IQ3_M | 15.7 | |\n| [GGUF](https://huggingface.co/mradermacher/aegolius-acadicus-34b-v3-i1-GGUF/resolve/main/aegolius-acadicus-34b-v3.i1-Q3_K_M.gguf) | i1-Q3_K_M | 17.1 | IQ3_S probably better |\n| [GGUF](https://huggingface.co/mradermacher/aegolius-acadicus-34b-v3-i1-GGUF/resolve/main/aegolius-acadicus-34b-v3.i1-Q3_K_L.gguf) | i1-Q3_K_L | 18.5 | IQ3_M probably better |\n| [GGUF](https://huggingface.co/mradermacher/aegolius-acadicus-34b-v3-i1-GGUF/resolve/main/aegolius-acadicus-34b-v3.i1-IQ4_XS.gguf) | i1-IQ4_XS | 19.0 | |\n| [GGUF](https://huggingface.co/mradermacher/aegolius-acadicus-34b-v3-i1-GGUF/resolve/main/aegolius-acadicus-34b-v3.i1-Q4_0.gguf) | i1-Q4_0 | 20.2 | fast, low quality |\n| [GGUF](https://huggingface.co/mradermacher/aegolius-acadicus-34b-v3-i1-GGUF/resolve/main/aegolius-acadicus-34b-v3.i1-Q4_K_S.gguf) | i1-Q4_K_S | 20.2 | optimal size/speed/quality |\n| [GGUF](https://huggingface.co/mradermacher/aegolius-acadicus-34b-v3-i1-GGUF/resolve/main/aegolius-acadicus-34b-v3.i1-Q4_K_M.gguf) | i1-Q4_K_M | 21.5 | fast, recommended |\n| [GGUF](https://huggingface.co/mradermacher/aegolius-acadicus-34b-v3-i1-GGUF/resolve/main/aegolius-acadicus-34b-v3.i1-Q5_K_S.gguf) | i1-Q5_K_S | 24.5 | |\n| [GGUF](https://huggingface.co/mradermacher/aegolius-acadicus-34b-v3-i1-GGUF/resolve/main/aegolius-acadicus-34b-v3.i1-Q5_K_M.gguf) | i1-Q5_K_M | 25.2 | |\n| [GGUF](https://huggingface.co/mradermacher/aegolius-acadicus-34b-v3-i1-GGUF/resolve/main/aegolius-acadicus-34b-v3.i1-Q6_K.gguf) | i1-Q6_K | 29.2 | practically like static Q6_K |\n\nHere is a handy graph by ikawrakow comparing some lower-quality quant\ntypes (lower is better):\n\n\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.\n\n<!-- end -->\n",
"related_quantizations": []
},
"tags": [
"transformers",
"gguf",
"moe",
"en",
"base_model:ibivibiv/aegolius-acadicus-34b-v3",
"base_model:quantized:ibivibiv/aegolius-acadicus-34b-v3",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
],
"likes": 0,
"downloads": 90,
"gated": false,
"private": false,
"last_modified": "2024-05-06T04:56:28.000Z",
"created_at": "2024-04-14T11:26:07.000Z",
"pipeline_tag": "",
"library_name": "transformers"
}
Source payload excerpt (from Hugging Face API)
{
"_id": "661bbd4f9f33c597832d8b0d",
"id": "mradermacher/aegolius-acadicus-34b-v3-i1-GGUF",
"modelId": "mradermacher/aegolius-acadicus-34b-v3-i1-GGUF",
"sha": "22abea947958a2fd878621d464f8487b90af6e39",
"createdAt": "2024-04-14T11:26:07.000Z",
"lastModified": "2024-05-06T04:56:28.000Z",
"author": "mradermacher",
"downloads": 90,
"likes": 0,
"gated": false,
"private": false,
"pipeline_tag": "",
"library_name": "transformers",
"siblings_count": 24
}