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

mradermacher/mlewd-remm-l2-chat-20b-i1-gguf overview

About weighted/imatrix quants of https://huggingface.co/Undi95/MLewd-ReMM-L2-Chat-20B static quants are available at https://huggingface.co/mradermacher/MLewd-ReMM-L2-Chat-20B-GGUF

transformersggufnot-for-all-audiencesnsfwenbase_model:Undi95/MLewd-ReMM-L2-Chat-20Bbase_model:quantized:Undi95/MLewd-ReMM-L2-Chat-20Blicense:cc-by-nc-4.0endpoints_compatibleregion:us
mradermacher/mlewd-remm-l2-chat-20b-i1-gguf visual
Downloads
100
Likes
6
Pipeline
Library
transformers
Visibility
Public
Access
Open

Repository Files & Downloads

22 files detected
Direct downloads for all repository files
FileTypeQuantizationSizeLink
MLewd-ReMM-L2-Chat-20B.i1-IQ1_M.gguf GGUF IQ1_M 4.64 GB Download
MLewd-ReMM-L2-Chat-20B.i1-IQ1_S.gguf GGUF IQ1_S 4.29 GB Download
MLewd-ReMM-L2-Chat-20B.i1-IQ2_M.gguf GGUF IQ2_M 6.62 GB Download
MLewd-ReMM-L2-Chat-20B.i1-IQ2_S.gguf GGUF IQ2_S 6.16 GB Download
MLewd-ReMM-L2-Chat-20B.i1-IQ2_XS.gguf GGUF IQ2_XS 5.73 GB Download
MLewd-ReMM-L2-Chat-20B.i1-IQ2_XXS.gguf GGUF IQ2_XXS 5.22 GB Download
MLewd-ReMM-L2-Chat-20B.i1-IQ3_M.gguf GGUF IQ3_M 8.71 GB Download
MLewd-ReMM-L2-Chat-20B.i1-IQ3_S.gguf GGUF IQ3_S 8.24 GB Download
MLewd-ReMM-L2-Chat-20B.i1-IQ3_XS.gguf GGUF IQ3_XS 7.81 GB Download
MLewd-ReMM-L2-Chat-20B.i1-IQ3_XXS.gguf GGUF IQ3_XXS 7.27 GB Download
MLewd-ReMM-L2-Chat-20B.i1-IQ4_NL.gguf GGUF IQ4_NL 10.70 GB Download
MLewd-ReMM-L2-Chat-20B.i1-IQ4_XS.gguf GGUF IQ4_XS 10.12 GB Download
MLewd-ReMM-L2-Chat-20B.i1-Q2_K.gguf GGUF Q2_K 7.09 GB Download
MLewd-ReMM-L2-Chat-20B.i1-Q3_K_L.gguf GGUF Q3_K_L 10.08 GB Download
MLewd-ReMM-L2-Chat-20B.i1-Q3_K_M.gguf GGUF Q3_K_M 9.22 GB Download
MLewd-ReMM-L2-Chat-20B.i1-Q3_K_S.gguf GGUF Q3_K_S 8.24 GB Download
MLewd-ReMM-L2-Chat-20B.i1-Q4_0.gguf GGUF 10.73 GB Download
MLewd-ReMM-L2-Chat-20B.i1-Q4_K_M.gguf GGUF Q4_K_M 11.40 GB Download
MLewd-ReMM-L2-Chat-20B.i1-Q4_K_S.gguf GGUF Q4_K_S 10.77 GB Download
MLewd-ReMM-L2-Chat-20B.i1-Q5_K_M.gguf GGUF Q5_K_M 13.36 GB Download
MLewd-ReMM-L2-Chat-20B.i1-Q5_K_S.gguf GGUF Q5_K_S 13.01 GB Download
MLewd-ReMM-L2-Chat-20B.i1-Q6_K.gguf GGUF Q6_K 15.46 GB Download

Model Details Live

Model Slug
mradermacher/mlewd-remm-l2-chat-20b-i1-gguf
Author
mradermacher
Pipeline Task
Library
transformers
Created
2024-03-29
Last Modified
2024-05-06
Gated
No
Private
No
HF SHA
9d2f52057cf9a77aa312fabd07b8ae923a479ce5
License
cc-by-nc-4.0
Language
en
Base Model
Undi95/MLewd-ReMM-L2-Chat-20B

Metadata Inspector

Normalized metadata (stored in metadata_json)
{
  "metadata": {},
  "card_data": {
    "base_model": "Undi95/MLewd-ReMM-L2-Chat-20B",
    "language": [
      "en"
    ],
    "library_name": "transformers",
    "license": "cc-by-nc-4.0",
    "quantized_by": "mradermacher",
    "tags": [
      "not-for-all-audiences",
      "nsfw"
    ],
    "frontmatter": {
      "base_model": "Undi95/MLewd-ReMM-L2-Chat-20B",
      "language": [
        "en"
      ],
      "library_name": "transformers",
      "license": "cc-by-nc-4.0",
      "quantized_by": "mradermacher",
      "tags": [
        "not-for-all-audiences",
        "nsfw"
      ]
    },
    "hero_image_url": "https://www.nethype.de/huggingface_embed/quantpplgraph.png",
    "summary": "## About weighted/imatrix quants of https://huggingface.co/Undi95/MLewd-ReMM-L2-Chat-20B  static quants are available at https://huggingface.co/mradermacher/MLewd-ReMM-L2-Chat-20B-GGUF",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: Undi95/MLewd-ReMM-L2-Chat-20B\nlanguage:\n- en\nlibrary_name: transformers\nlicense: cc-by-nc-4.0\nquantized_by: mradermacher\ntags:\n- not-for-all-audiences\n- nsfw\n---\n## About\n\nweighted/imatrix quants of https://huggingface.co/Undi95/MLewd-ReMM-L2-Chat-20B\n\n<!-- provided-files -->\nstatic quants are available at https://huggingface.co/mradermacher/MLewd-ReMM-L2-Chat-20B-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/MLewd-ReMM-L2-Chat-20B-i1-GGUF/resolve/main/MLewd-ReMM-L2-Chat-20B.i1-IQ1_S.gguf) | i1-IQ1_S | 4.7 | for the desperate |\n| [GGUF](https://huggingface.co/mradermacher/MLewd-ReMM-L2-Chat-20B-i1-GGUF/resolve/main/MLewd-ReMM-L2-Chat-20B.i1-IQ1_M.gguf) | i1-IQ1_M | 5.1 | mostly desperate |\n| [GGUF](https://huggingface.co/mradermacher/MLewd-ReMM-L2-Chat-20B-i1-GGUF/resolve/main/MLewd-ReMM-L2-Chat-20B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 5.7 |  |\n| [GGUF](https://huggingface.co/mradermacher/MLewd-ReMM-L2-Chat-20B-i1-GGUF/resolve/main/MLewd-ReMM-L2-Chat-20B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 6.3 |  |\n| [GGUF](https://huggingface.co/mradermacher/MLewd-ReMM-L2-Chat-20B-i1-GGUF/resolve/main/MLewd-ReMM-L2-Chat-20B.i1-IQ2_S.gguf) | i1-IQ2_S | 6.7 |  |\n| [GGUF](https://huggingface.co/mradermacher/MLewd-ReMM-L2-Chat-20B-i1-GGUF/resolve/main/MLewd-ReMM-L2-Chat-20B.i1-IQ2_M.gguf) | i1-IQ2_M | 7.2 |  |\n| [GGUF](https://huggingface.co/mradermacher/MLewd-ReMM-L2-Chat-20B-i1-GGUF/resolve/main/MLewd-ReMM-L2-Chat-20B.i1-Q2_K.gguf) | i1-Q2_K | 7.7 | IQ3_XXS probably better |\n| [GGUF](https://huggingface.co/mradermacher/MLewd-ReMM-L2-Chat-20B-i1-GGUF/resolve/main/MLewd-ReMM-L2-Chat-20B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 7.9 | lower quality |\n| [GGUF](https://huggingface.co/mradermacher/MLewd-ReMM-L2-Chat-20B-i1-GGUF/resolve/main/MLewd-ReMM-L2-Chat-20B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 8.5 |  |\n| [GGUF](https://huggingface.co/mradermacher/MLewd-ReMM-L2-Chat-20B-i1-GGUF/resolve/main/MLewd-ReMM-L2-Chat-20B.i1-IQ3_S.gguf) | i1-IQ3_S | 9.0 | beats Q3_K* |\n| [GGUF](https://huggingface.co/mradermacher/MLewd-ReMM-L2-Chat-20B-i1-GGUF/resolve/main/MLewd-ReMM-L2-Chat-20B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 9.0 | IQ3_XS probably better |\n| [GGUF](https://huggingface.co/mradermacher/MLewd-ReMM-L2-Chat-20B-i1-GGUF/resolve/main/MLewd-ReMM-L2-Chat-20B.i1-IQ3_M.gguf) | i1-IQ3_M | 9.4 |  |\n| [GGUF](https://huggingface.co/mradermacher/MLewd-ReMM-L2-Chat-20B-i1-GGUF/resolve/main/MLewd-ReMM-L2-Chat-20B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 10.0 | IQ3_S probably better |\n| [GGUF](https://huggingface.co/mradermacher/MLewd-ReMM-L2-Chat-20B-i1-GGUF/resolve/main/MLewd-ReMM-L2-Chat-20B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 10.9 | IQ3_M probably better |\n| [GGUF](https://huggingface.co/mradermacher/MLewd-ReMM-L2-Chat-20B-i1-GGUF/resolve/main/MLewd-ReMM-L2-Chat-20B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 11.0 |  |\n| [GGUF](https://huggingface.co/mradermacher/MLewd-ReMM-L2-Chat-20B-i1-GGUF/resolve/main/MLewd-ReMM-L2-Chat-20B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 11.6 | prefer IQ4_XS |\n| [GGUF](https://huggingface.co/mradermacher/MLewd-ReMM-L2-Chat-20B-i1-GGUF/resolve/main/MLewd-ReMM-L2-Chat-20B.i1-Q4_0.gguf) | i1-Q4_0 | 11.6 | fast, low quality |\n| [GGUF](https://huggingface.co/mradermacher/MLewd-ReMM-L2-Chat-20B-i1-GGUF/resolve/main/MLewd-ReMM-L2-Chat-20B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 11.7 | optimal size/speed/quality |\n| [GGUF](https://huggingface.co/mradermacher/MLewd-ReMM-L2-Chat-20B-i1-GGUF/resolve/main/MLewd-ReMM-L2-Chat-20B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 12.3 | fast, recommended |\n| [GGUF](https://huggingface.co/mradermacher/MLewd-ReMM-L2-Chat-20B-i1-GGUF/resolve/main/MLewd-ReMM-L2-Chat-20B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 14.1 |  |\n| [GGUF](https://huggingface.co/mradermacher/MLewd-ReMM-L2-Chat-20B-i1-GGUF/resolve/main/MLewd-ReMM-L2-Chat-20B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 14.5 |  |\n| [GGUF](https://huggingface.co/mradermacher/MLewd-ReMM-L2-Chat-20B-i1-GGUF/resolve/main/MLewd-ReMM-L2-Chat-20B.i1-Q6_K.gguf) | i1-Q6_K | 16.7 | 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.\n\n<!-- end -->\n",
    "related_quantizations": []
  },
  "tags": [
    "transformers",
    "gguf",
    "not-for-all-audiences",
    "nsfw",
    "en",
    "base_model:Undi95/MLewd-ReMM-L2-Chat-20B",
    "base_model:quantized:Undi95/MLewd-ReMM-L2-Chat-20B",
    "license:cc-by-nc-4.0",
    "endpoints_compatible",
    "region:us"
  ],
  "likes": 6,
  "downloads": 100,
  "gated": false,
  "private": false,
  "last_modified": "2024-05-06T05:35:35.000Z",
  "created_at": "2024-03-29T21:30:26.000Z",
  "pipeline_tag": "",
  "library_name": "transformers"
}
Source payload excerpt (from Hugging Face API)
{
  "_id": "660732f244a011983bad4c13",
  "id": "mradermacher/MLewd-ReMM-L2-Chat-20B-i1-GGUF",
  "modelId": "mradermacher/MLewd-ReMM-L2-Chat-20B-i1-GGUF",
  "sha": "9d2f52057cf9a77aa312fabd07b8ae923a479ce5",
  "createdAt": "2024-03-29T21:30:26.000Z",
  "lastModified": "2024-05-06T05:35:35.000Z",
  "author": "mradermacher",
  "downloads": 100,
  "likes": 6,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "transformers",
  "siblings_count": 25
}