Model Intelligence Sheet
mradermacher/midnight-miqu-70b-v1.0-i1-gguf overview
About weighted/imatrix quants of https://huggingface.co/sophosympatheia/Midnight-Miqu-70B-v1.0 static quants are available at https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-GGUF
Downloads
154
Likes
10
Pipeline
—
Library
transformers
Visibility
Public
Access
Open
Repository Files & Downloads
21 files detected
Direct downloads for all repository files
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Midnight-Miqu-70B-v1.0.i1-IQ1_M.gguf | GGUF | IQ1_M | 14.85 GB | Download |
| Midnight-Miqu-70B-v1.0.i1-IQ1_S.gguf | GGUF | IQ1_S | 13.86 GB | Download |
| Midnight-Miqu-70B-v1.0.i1-IQ2_M.gguf | GGUF | IQ2_M | 21.96 GB | Download |
| Midnight-Miqu-70B-v1.0.i1-IQ2_S.gguf | GGUF | IQ2_S | 20.21 GB | Download |
| Midnight-Miqu-70B-v1.0.i1-IQ2_XS.gguf | GGUF | IQ2_XS | 19.26 GB | Download |
| Midnight-Miqu-70B-v1.0.i1-IQ2_XXS.gguf | GGUF | IQ2_XXS | 17.35 GB | Download |
| Midnight-Miqu-70B-v1.0.i1-IQ3_M.gguf | GGUF | IQ3_M | 29.11 GB | Download |
| Midnight-Miqu-70B-v1.0.i1-IQ3_S.gguf | GGUF | IQ3_S | 28.15 GB | Download |
| Midnight-Miqu-70B-v1.0.i1-IQ3_XS.gguf | GGUF | IQ3_XS | 26.50 GB | Download |
| Midnight-Miqu-70B-v1.0.i1-IQ3_XXS.gguf | GGUF | IQ3_XXS | 25.08 GB | Download |
| Midnight-Miqu-70B-v1.0.i1-IQ4_NL.gguf | GGUF | IQ4_NL | 36.57 GB | Download |
| Midnight-Miqu-70B-v1.0.i1-IQ4_XS.gguf | GGUF | IQ4_XS | 34.59 GB | Download |
| Midnight-Miqu-70B-v1.0.i1-Q2_K.gguf | GGUF | Q2_K | 24.00 GB | Download |
| Midnight-Miqu-70B-v1.0.i1-Q3_K_L.gguf | GGUF | Q3_K_L | 33.95 GB | Download |
| Midnight-Miqu-70B-v1.0.i1-Q3_K_M.gguf | GGUF | Q3_K_M | 31.28 GB | Download |
| Midnight-Miqu-70B-v1.0.i1-Q3_K_S.gguf | GGUF | Q3_K_S | 28.15 GB | Download |
| Midnight-Miqu-70B-v1.0.i1-Q4_0.gguf | GGUF | — | 36.63 GB | Download |
| Midnight-Miqu-70B-v1.0.i1-Q4_K_M.gguf | GGUF | Q4_K_M | 38.87 GB | Download |
| Midnight-Miqu-70B-v1.0.i1-Q4_K_S.gguf | GGUF | Q4_K_S | 36.84 GB | Download |
| Midnight-Miqu-70B-v1.0.i1-Q5_K_M.gguf | GGUF | Q5_K_M | 45.69 GB | Download |
| Midnight-Miqu-70B-v1.0.i1-Q5_K_S.gguf | GGUF | Q5_K_S | 44.49 GB | Download |
Model Details Live
Metadata Inspector
Normalized metadata (stored in metadata_json)
{
"metadata": {},
"card_data": {
"base_model": "sophosympatheia/Midnight-Miqu-70B-v1.0",
"language": [
"en"
],
"library_name": "transformers",
"license": "other",
"quantized_by": "mradermacher",
"tags": [
"mergekit",
"merge"
],
"frontmatter": {
"base_model": "sophosympatheia/Midnight-Miqu-70B-v1.0",
"language": [
"en"
],
"library_name": "transformers",
"license": "other",
"quantized_by": "mradermacher",
"tags": [
"mergekit",
"merge"
]
},
"hero_image_url": "https://www.nethype.de/huggingface_embed/quantpplgraph.png",
"summary": "## About weighted/imatrix quants of https://huggingface.co/sophosympatheia/Midnight-Miqu-70B-v1.0 static quants are available at https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-GGUF",
"quick_links": [],
"benchmark_table_html": "",
"readme_markdown": "---\nbase_model: sophosympatheia/Midnight-Miqu-70B-v1.0\nlanguage:\n- en\nlibrary_name: transformers\nlicense: other\nquantized_by: mradermacher\ntags:\n- mergekit\n- merge\n---\n## About\n\nweighted/imatrix quants of https://huggingface.co/sophosympatheia/Midnight-Miqu-70B-v1.0\n\n<!-- provided-files -->\nstatic quants are available at https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-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/Midnight-Miqu-70B-v1.0-i1-GGUF/resolve/main/Midnight-Miqu-70B-v1.0.i1-IQ1_S.gguf) | i1-IQ1_S | 15.0 | for the desperate |\n| [GGUF](https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-i1-GGUF/resolve/main/Midnight-Miqu-70B-v1.0.i1-IQ1_M.gguf) | i1-IQ1_M | 16.0 | mostly desperate |\n| [GGUF](https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-i1-GGUF/resolve/main/Midnight-Miqu-70B-v1.0.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 18.7 | |\n| [GGUF](https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-i1-GGUF/resolve/main/Midnight-Miqu-70B-v1.0.i1-IQ2_XS.gguf) | i1-IQ2_XS | 20.8 | |\n| [GGUF](https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-i1-GGUF/resolve/main/Midnight-Miqu-70B-v1.0.i1-IQ2_S.gguf) | i1-IQ2_S | 21.8 | |\n| [GGUF](https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-i1-GGUF/resolve/main/Midnight-Miqu-70B-v1.0.i1-IQ2_M.gguf) | i1-IQ2_M | 23.7 | |\n| [GGUF](https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-i1-GGUF/resolve/main/Midnight-Miqu-70B-v1.0.i1-Q2_K.gguf) | i1-Q2_K | 25.9 | IQ3_XXS probably better |\n| [GGUF](https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-i1-GGUF/resolve/main/Midnight-Miqu-70B-v1.0.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 27.0 | lower quality |\n| [GGUF](https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-i1-GGUF/resolve/main/Midnight-Miqu-70B-v1.0.i1-IQ3_XS.gguf) | i1-IQ3_XS | 28.6 | |\n| [GGUF](https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-i1-GGUF/resolve/main/Midnight-Miqu-70B-v1.0.i1-IQ3_S.gguf) | i1-IQ3_S | 30.3 | beats Q3_K* |\n| [GGUF](https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-i1-GGUF/resolve/main/Midnight-Miqu-70B-v1.0.i1-Q3_K_S.gguf) | i1-Q3_K_S | 30.3 | IQ3_XS probably better |\n| [GGUF](https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-i1-GGUF/resolve/main/Midnight-Miqu-70B-v1.0.i1-IQ3_M.gguf) | i1-IQ3_M | 31.4 | |\n| [GGUF](https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-i1-GGUF/resolve/main/Midnight-Miqu-70B-v1.0.i1-Q3_K_M.gguf) | i1-Q3_K_M | 33.7 | IQ3_S probably better |\n| [GGUF](https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-i1-GGUF/resolve/main/Midnight-Miqu-70B-v1.0.i1-Q3_K_L.gguf) | i1-Q3_K_L | 36.6 | IQ3_M probably better |\n| [GGUF](https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-i1-GGUF/resolve/main/Midnight-Miqu-70B-v1.0.i1-IQ4_XS.gguf) | i1-IQ4_XS | 37.2 | |\n| [GGUF](https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-i1-GGUF/resolve/main/Midnight-Miqu-70B-v1.0.i1-IQ4_NL.gguf) | i1-IQ4_NL | 39.4 | prefer IQ4_XS |\n| [GGUF](https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-i1-GGUF/resolve/main/Midnight-Miqu-70B-v1.0.i1-Q4_0.gguf) | i1-Q4_0 | 39.4 | fast, low quality |\n| [GGUF](https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-i1-GGUF/resolve/main/Midnight-Miqu-70B-v1.0.i1-Q4_K_S.gguf) | i1-Q4_K_S | 39.7 | optimal size/speed/quality |\n| [GGUF](https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-i1-GGUF/resolve/main/Midnight-Miqu-70B-v1.0.i1-Q4_K_M.gguf) | i1-Q4_K_M | 41.8 | fast, recommended |\n| [GGUF](https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-i1-GGUF/resolve/main/Midnight-Miqu-70B-v1.0.i1-Q5_K_S.gguf) | i1-Q5_K_S | 47.9 | |\n| [GGUF](https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-i1-GGUF/resolve/main/Midnight-Miqu-70B-v1.0.i1-Q5_K_M.gguf) | i1-Q5_K_M | 49.2 | |\n| [PART 1](https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-i1-GGUF/resolve/main/Midnight-Miqu-70B-v1.0.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Midnight-Miqu-70B-v1.0-i1-GGUF/resolve/main/Midnight-Miqu-70B-v1.0.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 57.0 | 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",
"mergekit",
"merge",
"en",
"base_model:sophosympatheia/Midnight-Miqu-70B-v1.0",
"base_model:quantized:sophosympatheia/Midnight-Miqu-70B-v1.0",
"license:other",
"endpoints_compatible",
"region:us",
"conversational"
],
"likes": 10,
"downloads": 154,
"gated": false,
"private": false,
"last_modified": "2024-05-06T06:20:44.000Z",
"created_at": "2024-03-02T19:05:24.000Z",
"pipeline_tag": "",
"library_name": "transformers"
}
Source payload excerpt (from Hugging Face API)
{
"_id": "65e37874400c626ca053b3fd",
"id": "mradermacher/Midnight-Miqu-70B-v1.0-i1-GGUF",
"modelId": "mradermacher/Midnight-Miqu-70B-v1.0-i1-GGUF",
"sha": "44a7c391f0ba2654f98e863ad5afe342d10cae35",
"createdAt": "2024-03-02T19:05:24.000Z",
"lastModified": "2024-05-06T06:20:44.000Z",
"author": "mradermacher",
"downloads": 154,
"likes": 10,
"gated": false,
"private": false,
"pipeline_tag": "",
"library_name": "transformers",
"siblings_count": 26
}