GraySoft
Projects Models About FAQ Contact Download guIDE →

mmnga/sarashina2.2-3b-instruct-v0.1-gguf IQ3_XXS 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

mmnga/sarashina2.2-3b-instruct-v0.1-gguf overview

sbintuitionsさんが公開しているsarashina2.2-3b-instruct-v0.1のggufフォーマット変換版です。 imatrixのデータはTFMC/imatrix-dataset-for-japanese-llmを使用して作成しました。

ggufenjadataset:TFMC/imatrix-dataset-for-japanese-llmbase_model:sbintuitions/sarashina2.2-3b-instruct-v0.1base_model:quantized:sbintuitions/sarashina2.2-3b-instruct-v0.1license:mitendpoints_compatibleregion:usimatrixconversational
mmnga/sarashina2.2-3b-instruct-v0.1-gguf visual
Downloads
239
Likes
8
Pipeline
Library
Visibility
Public
Access
Open

Repository Files & Downloads

24 files detected
Direct downloads for all repository files
FileTypeQuantizationSizeLink
sarashina2.2-3b-instruct-v0.1-IQ1_M.gguf GGUF IQ1_M 875.94 MB Download
sarashina2.2-3b-instruct-v0.1-IQ1_S.gguf GGUF IQ1_S 821.74 MB Download
sarashina2.2-3b-instruct-v0.1-IQ2_M.gguf GGUF IQ2_M 1.16 GB Download
sarashina2.2-3b-instruct-v0.1-IQ2_S.gguf GGUF IQ2_S 1.09 GB Download
sarashina2.2-3b-instruct-v0.1-IQ2_XS.gguf GGUF IQ2_XS 1.02 GB Download
sarashina2.2-3b-instruct-v0.1-IQ2_XXS.gguf GGUF IQ2_XXS 966.27 MB Download
sarashina2.2-3b-instruct-v0.1-IQ3_M.gguf GGUF IQ3_M 1.49 GB Download
sarashina2.2-3b-instruct-v0.1-IQ3_S.gguf GGUF IQ3_S 1.44 GB Download
sarashina2.2-3b-instruct-v0.1-IQ3_XS.gguf GGUF IQ3_XS 1.38 GB Download
sarashina2.2-3b-instruct-v0.1-IQ3_XXS.gguf GGUF IQ3_XXS 1.28 GB Download
sarashina2.2-3b-instruct-v0.1-IQ4_NL.gguf GGUF IQ4_NL 1.82 GB Download
sarashina2.2-3b-instruct-v0.1-IQ4_XS.gguf GGUF IQ4_XS 1.73 GB Download
sarashina2.2-3b-instruct-v0.1-Q2_K.gguf GGUF Q2_K 1.25 GB Download
sarashina2.2-3b-instruct-v0.1-Q3_K_L.gguf GGUF Q3_K_L 1.69 GB Download
sarashina2.2-3b-instruct-v0.1-Q3_K_M.gguf GGUF Q3_K_M 1.58 GB Download
sarashina2.2-3b-instruct-v0.1-Q3_K_S.gguf GGUF Q3_K_S 1.44 GB Download
sarashina2.2-3b-instruct-v0.1-Q4_0.gguf GGUF 1.82 GB Download
sarashina2.2-3b-instruct-v0.1-Q4_K_M.gguf GGUF Q4_K_M 1.92 GB Download
sarashina2.2-3b-instruct-v0.1-Q4_K_S.gguf GGUF Q4_K_S 1.84 GB Download
sarashina2.2-3b-instruct-v0.1-Q5_0.gguf GGUF 2.18 GB Download
sarashina2.2-3b-instruct-v0.1-Q5_K_M.gguf GGUF Q5_K_M 2.24 GB Download
sarashina2.2-3b-instruct-v0.1-Q5_K_S.gguf GGUF Q5_K_S 2.18 GB Download
sarashina2.2-3b-instruct-v0.1-Q6_K.gguf GGUF Q6_K 2.57 GB Download
sarashina2.2-3b-instruct-v0.1-Q8_0.gguf GGUF 3.32 GB Download

Model Details Live

Model Slug
mmnga/sarashina2.2-3b-instruct-v0.1-gguf
Author
mmnga
Pipeline Task
Library
Created
2025-03-05
Last Modified
2025-03-05
Gated
No
Private
No
HF SHA
31d771319b04032f33e0d9d860f3984ea4812154
License
mit
Language
en, ja
Base Model
sbintuitions/sarashina2.2-3b-instruct-v0.1

Metadata Inspector

Normalized metadata (stored in metadata_json)
{
  "metadata": {},
  "card_data": {
    "license": "mit",
    "language": [
      "en",
      "ja"
    ],
    "datasets": [
      "TFMC/imatrix-dataset-for-japanese-llm"
    ],
    "base_model": [
      "sbintuitions/sarashina2.2-3b-instruct-v0.1"
    ],
    "frontmatter": {
      "license": "mit",
      "language": [
        "en",
        "ja"
      ],
      "datasets": [
        "TFMC/imatrix-dataset-for-japanese-llm"
      ],
      "base_model": [
        "sbintuitions/sarashina2.2-3b-instruct-v0.1"
      ]
    },
    "hero_image_url": "",
    "summary": "sbintuitionsさんが公開しているsarashina2.2-3b-instruct-v0.1のggufフォーマット変換版です。 imatrixのデータはTFMC/imatrix-dataset-for-japanese-llmを使用して作成しました。",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlicense: mit\nlanguage:\n- en\n- ja\ndatasets:\n- TFMC/imatrix-dataset-for-japanese-llm\nbase_model:\n- sbintuitions/sarashina2.2-3b-instruct-v0.1\n---\n\n# sarashina2.2-3b-instruct-v0.1-gguf\n[sbintuitionsさんが公開しているsarashina2.2-3b-instruct-v0.1](https://huggingface.co/sbintuitions/sarashina2.2-3b-instruct-v0.1)のggufフォーマット変換版です。  \n\nimatrixのデータは[TFMC/imatrix-dataset-for-japanese-llm](https://huggingface.co/datasets/TFMC/imatrix-dataset-for-japanese-llm)を使用して作成しました。  \n  \n## Usage\n\n```\ngit clone https://github.com/ggerganov/llama.cpp.git\ncd llama.cpp\ncmake -B build -DGGML_CUDA=ON\ncmake --build build --config Release\nbuild/bin/llama-cli -m 'sarashina2.2-3b-instruct-v0.1-gguf' -n 128 -c 128 -p 'あなたはプロの料理人です。レシピを教えて' -cnv\n```",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "en",
    "ja",
    "dataset:TFMC/imatrix-dataset-for-japanese-llm",
    "base_model:sbintuitions/sarashina2.2-3b-instruct-v0.1",
    "base_model:quantized:sbintuitions/sarashina2.2-3b-instruct-v0.1",
    "license:mit",
    "endpoints_compatible",
    "region:us",
    "imatrix",
    "conversational"
  ],
  "likes": 8,
  "downloads": 239,
  "gated": false,
  "private": false,
  "last_modified": "2025-03-05T16:20:38.000Z",
  "created_at": "2025-03-05T07:56:41.000Z",
  "pipeline_tag": "",
  "library_name": ""
}
Source payload excerpt (from Hugging Face API)
{
  "_id": "67c803b908ea8978b9739215",
  "id": "mmnga/sarashina2.2-3b-instruct-v0.1-gguf",
  "modelId": "mmnga/sarashina2.2-3b-instruct-v0.1-gguf",
  "sha": "31d771319b04032f33e0d9d860f3984ea4812154",
  "createdAt": "2025-03-05T07:56:41.000Z",
  "lastModified": "2025-03-05T16:20:38.000Z",
  "author": "mmnga",
  "downloads": 239,
  "likes": 8,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 26
}