mmnga/llama-4-scout-17b-16e-instruct-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/llama-4-scout-17b-16e-instruct-gguf overview
meta-llamaさんが公開しているLlama-4-Scout-17B-16E-Instruct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。
Downloads
100
Likes
2
Pipeline
—
Library
—
Visibility
Public
Access
Open
Repository Files & Downloads
12 files detected
Direct downloads for all repository files
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Llama-4-Scout-17B-16E-Instruct-IQ1_M.gguf | GGUF | IQ1_M | 22.88 GB | Download |
| Llama-4-Scout-17B-16E-Instruct-IQ1_S.gguf | GGUF | IQ1_S | 20.66 GB | Download |
| Llama-4-Scout-17B-16E-Instruct-IQ2_M.gguf | GGUF | IQ2_M | 33.04 GB | Download |
| Llama-4-Scout-17B-16E-Instruct-IQ2_S.gguf | GGUF | IQ2_S | 30.07 GB | Download |
| Llama-4-Scout-17B-16E-Instruct-IQ2_XS.gguf | GGUF | IQ2_XS | 29.60 GB | Download |
| Llama-4-Scout-17B-16E-Instruct-IQ2_XXS.gguf | GGUF | IQ2_XXS | 26.60 GB | Download |
| Llama-4-Scout-17B-16E-Instruct-IQ3_M.gguf | GGUF | IQ3_M | 44.25 GB | Download |
| Llama-4-Scout-17B-16E-Instruct-IQ3_S.gguf | GGUF | IQ3_S | 43.56 GB | Download |
| Llama-4-Scout-17B-16E-Instruct-IQ3_XS.gguf | GGUF | IQ3_XS | 41.25 GB | Download |
| Llama-4-Scout-17B-16E-Instruct-IQ3_XXS.gguf | GGUF | IQ3_XXS | 38.80 GB | Download |
| Llama-4-Scout-17B-16E-Instruct-Q2_K.gguf | GGUF | Q2_K | 36.85 GB | Download |
| Llama-4-Scout-17B-16E-Instruct-Q3_K_S.gguf | GGUF | Q3_K_S | 43.53 GB | Download |
Model Details Live
Metadata Inspector
Normalized metadata (stored in metadata_json)
{
"metadata": {},
"card_data": {
"license": "unknown",
"language": [
"en",
"ja"
],
"datasets": [
"TFMC/imatrix-dataset-for-japanese-llm"
],
"base_model": [
"meta-llama/Llama-4-Scout-17B-16E-Instruct"
],
"frontmatter": {},
"hero_image_url": "",
"summary": "meta-llamaさんが公開しているLlama-4-Scout-17B-16E-Instruct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": "\n---\nlicense: unknown\nlanguage:\n- en\n- ja\ndatasets:\n- TFMC/imatrix-dataset-for-japanese-llm\nbase_model:\n- meta-llama/Llama-4-Scout-17B-16E-Instruct\n---\n\n# Llama-4-Scout-17B-16E-Instruct-gguf\n[meta-llamaさんが公開しているLlama-4-Scout-17B-16E-Instruct](https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct)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/ggml-org/llama.cpp.git\ncd llama.cpp\ncmake -B build -DGGML_CUDA=ON\ncmake --build build --config Release\nbuild/bin/llama-cli -m 'Llama-4-Scout-17B-16E-Instruct-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```\n",
"related_quantizations": []
},
"tags": [
"gguf",
"en",
"ja",
"dataset:TFMC/imatrix-dataset-for-japanese-llm",
"base_model:meta-llama/Llama-4-Scout-17B-16E-Instruct",
"base_model:quantized:meta-llama/Llama-4-Scout-17B-16E-Instruct",
"license:unknown",
"endpoints_compatible",
"region:us",
"imatrix",
"conversational"
],
"likes": 2,
"downloads": 100,
"gated": false,
"private": false,
"last_modified": "2025-04-10T07:45:41.000Z",
"created_at": "2025-04-09T10:33:39.000Z",
"pipeline_tag": "",
"library_name": ""
}
Source payload excerpt (from Hugging Face API)
{
"_id": "67f64d0340e20d9e7600be11",
"id": "mmnga/Llama-4-Scout-17B-16E-Instruct-gguf",
"modelId": "mmnga/Llama-4-Scout-17B-16E-Instruct-gguf",
"sha": "16c8df2df3579cbf847c6c67701ee997d0c7df59",
"createdAt": "2025-04-09T10:33:39.000Z",
"lastModified": "2025-04-10T07:45:41.000Z",
"author": "mmnga",
"downloads": 100,
"likes": 2,
"gated": false,
"private": false,
"pipeline_tag": "",
"library_name": "",
"siblings_count": 39
}