mmnga/moonlight-16b-a3b-instruct-gguf Q5_0 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/moonlight-16b-a3b-instruct-gguf overview
moonshotaiさんが公開しているMoonlight-16B-A3B-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
359
Likes
13
Pipeline
—
Library
—
Visibility
Public
Access
Open
Repository Files & Downloads
24 files detected
Direct downloads for all repository files
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Moonlight-16B-A3B-Instruct-IQ1_M.gguf | GGUF | IQ1_M | 4.99 GB | Download |
| Moonlight-16B-A3B-Instruct-IQ1_S.gguf | GGUF | IQ1_S | 4.77 GB | Download |
| Moonlight-16B-A3B-Instruct-IQ2_M.gguf | GGUF | IQ2_M | 6.03 GB | Download |
| Moonlight-16B-A3B-Instruct-IQ2_S.gguf | GGUF | IQ2_S | 5.72 GB | Download |
| Moonlight-16B-A3B-Instruct-IQ2_XS.gguf | GGUF | IQ2_XS | 5.67 GB | Download |
| Moonlight-16B-A3B-Instruct-IQ2_XXS.gguf | GGUF | IQ2_XXS | 5.37 GB | Download |
| Moonlight-16B-A3B-Instruct-IQ3_M.gguf | GGUF | IQ3_M | 7.18 GB | Download |
| Moonlight-16B-A3B-Instruct-IQ3_S.gguf | GGUF | IQ3_S | 7.12 GB | Download |
| Moonlight-16B-A3B-Instruct-IQ3_XS.gguf | GGUF | IQ3_XS | 6.78 GB | Download |
| Moonlight-16B-A3B-Instruct-IQ3_XXS.gguf | GGUF | IQ3_XXS | 6.62 GB | Download |
| Moonlight-16B-A3B-Instruct-IQ4_NL.gguf | GGUF | IQ4_NL | 8.46 GB | Download |
| Moonlight-16B-A3B-Instruct-IQ4_XS.gguf | GGUF | IQ4_XS | 8.14 GB | Download |
| Moonlight-16B-A3B-Instruct-Q2_K.gguf | GGUF | Q2_K | 6.12 GB | Download |
| Moonlight-16B-A3B-Instruct-Q3_K_L.gguf | GGUF | Q3_K_L | 8.03 GB | Download |
| Moonlight-16B-A3B-Instruct-Q3_K_M.gguf | GGUF | Q3_K_M | 7.72 GB | Download |
| Moonlight-16B-A3B-Instruct-Q3_K_S.gguf | GGUF | Q3_K_S | 7.12 GB | Download |
| Moonlight-16B-A3B-Instruct-Q4_0.gguf | GGUF | — | 8.46 GB | Download |
| Moonlight-16B-A3B-Instruct-Q4_K_M.gguf | GGUF | Q4_K_M | 9.81 GB | Download |
| Moonlight-16B-A3B-Instruct-Q4_K_S.gguf | GGUF | Q4_K_S | 9.04 GB | Download |
| Moonlight-16B-A3B-Instruct-Q5_0.gguf | GGUF | — | 10.28 GB | Download |
| Moonlight-16B-A3B-Instruct-Q5_K_M.gguf | GGUF | Q5_K_M | 11.21 GB | Download |
| Moonlight-16B-A3B-Instruct-Q5_K_S.gguf | GGUF | Q5_K_S | 10.56 GB | Download |
| Moonlight-16B-A3B-Instruct-Q6_K.gguf | GGUF | Q6_K | 13.29 GB | Download |
| Moonlight-16B-A3B-Instruct-Q8_0.gguf | GGUF | — | 15.81 GB | Download |
Model Details Live
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": [
"moonshotai/Moonlight-16B-A3B-Instruct"
],
"frontmatter": {},
"hero_image_url": "",
"summary": "moonshotaiさんが公開しているMoonlight-16B-A3B-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: mit\nlanguage:\n- en\n- ja\ndatasets:\n- TFMC/imatrix-dataset-for-japanese-llm\nbase_model:\n- moonshotai/Moonlight-16B-A3B-Instruct\n---\n\n# Moonlight-16B-A3B-Instruct-gguf\n[moonshotaiさんが公開しているMoonlight-16B-A3B-Instruct](https://huggingface.co/moonshotai/Moonlight-16B-A3B-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\nchat-templateはカスタムのため除去してあります。 \nお試し用でお願いします。\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 'Moonlight-16B-A3B-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'\n```\n",
"related_quantizations": []
},
"tags": [
"gguf",
"en",
"ja",
"dataset:TFMC/imatrix-dataset-for-japanese-llm",
"base_model:moonshotai/Moonlight-16B-A3B-Instruct",
"base_model:quantized:moonshotai/Moonlight-16B-A3B-Instruct",
"license:mit",
"endpoints_compatible",
"region:us",
"imatrix"
],
"likes": 13,
"downloads": 359,
"gated": false,
"private": false,
"last_modified": "2025-02-23T19:50:28.000Z",
"created_at": "2025-02-23T17:11:42.000Z",
"pipeline_tag": "",
"library_name": ""
}
Source payload excerpt (from Hugging Face API)
{
"_id": "67bb56cee8558463aa5f0247",
"id": "mmnga/Moonlight-16B-A3B-Instruct-gguf",
"modelId": "mmnga/Moonlight-16B-A3B-Instruct-gguf",
"sha": "eb4728b376af0f3e168dc96d23cd21818c5738f6",
"createdAt": "2025-02-23T17:11:42.000Z",
"lastModified": "2025-02-23T19:50:28.000Z",
"author": "mmnga",
"downloads": 359,
"likes": 13,
"gated": false,
"private": false,
"pipeline_tag": "",
"library_name": "",
"siblings_count": 26
}