mmnga-o/arrowcanaria-llama-8b-sft-v0.1-gguf MXFP4_MOE 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-o/arrowcanaria-llama-8b-sft-v0.1-gguf overview
DataPilotさんが公開しているArrowCanaria-Llama-8B-SFT-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。
Downloads
2,292
Likes
4
Pipeline
—
Library
—
Visibility
Public
Access
Open
Repository Files & Downloads
14 files detected
Direct downloads for all repository files
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| ArrowCanaria-Llama-8B-SFT-v0.1-IQ3_M.gguf | GGUF | IQ3_M | 3.52 GB | Download |
| ArrowCanaria-Llama-8B-SFT-v0.1-IQ4_NL.gguf | GGUF | IQ4_NL | 4.36 GB | Download |
| ArrowCanaria-Llama-8B-SFT-v0.1-IQ4_XS.gguf | GGUF | IQ4_XS | 4.14 GB | Download |
| ArrowCanaria-Llama-8B-SFT-v0.1-MXFP4_MOE.gguf | GGUF | — | 7.95 GB | Download |
| ArrowCanaria-Llama-8B-SFT-v0.1-Q3_K_L.gguf | GGUF | Q3_K_L | 4.03 GB | Download |
| ArrowCanaria-Llama-8B-SFT-v0.1-Q3_K_M.gguf | GGUF | Q3_K_M | 3.74 GB | Download |
| ArrowCanaria-Llama-8B-SFT-v0.1-Q4_0.gguf | GGUF | — | 4.34 GB | Download |
| ArrowCanaria-Llama-8B-SFT-v0.1-Q4_K_M.gguf | GGUF | Q4_K_M | 4.58 GB | Download |
| ArrowCanaria-Llama-8B-SFT-v0.1-Q4_K_S.gguf | GGUF | Q4_K_S | 4.37 GB | Download |
| ArrowCanaria-Llama-8B-SFT-v0.1-Q5_0.gguf | GGUF | — | 5.21 GB | Download |
| ArrowCanaria-Llama-8B-SFT-v0.1-Q5_K_M.gguf | GGUF | Q5_K_M | 5.34 GB | Download |
| ArrowCanaria-Llama-8B-SFT-v0.1-Q5_K_S.gguf | GGUF | Q5_K_S | 5.21 GB | Download |
| ArrowCanaria-Llama-8B-SFT-v0.1-Q6_K.gguf | GGUF | Q6_K | 6.14 GB | Download |
| ArrowCanaria-Llama-8B-SFT-v0.1-Q8_0.gguf | GGUF | — | 7.95 GB | Download |
Model Details Live
Metadata Inspector
Normalized metadata (stored in metadata_json)
{
"metadata": {},
"card_data": {
"license": "llama3.3",
"language": [
"ja"
],
"datasets": [
"TFMC/imatrix-dataset-for-japanese-llm"
],
"base_model": [
"DataPilot/ArrowCanaria-Llama-8B-SFT-v0.1"
],
"frontmatter": {},
"hero_image_url": "",
"summary": "DataPilotさんが公開しているArrowCanaria-Llama-8B-SFT-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": "\n---\nlicense: llama3.3\nlanguage:\n- ja\ndatasets:\n- TFMC/imatrix-dataset-for-japanese-llm\nbase_model:\n- DataPilot/ArrowCanaria-Llama-8B-SFT-v0.1\n---\n\n# ArrowCanaria-Llama-8B-SFT-v0.1-gguf\n[DataPilotさんが公開しているArrowCanaria-Llama-8B-SFT-v0.1](https://huggingface.co/DataPilot/ArrowCanaria-Llama-8B-SFT-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/ggml-org/llama.cpp.git\ncd llama.cpp\ncmake -B build -DGGML_CUDA=ON\ncmake --build build --config Release\nbuild/bin/llama-cli -m 'ArrowCanaria-Llama-8B-SFT-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```\n",
"related_quantizations": []
},
"tags": [
"gguf",
"ja",
"dataset:TFMC/imatrix-dataset-for-japanese-llm",
"base_model:DataPilot/ArrowCanaria-Llama-8B-SFT-v0.1",
"base_model:quantized:DataPilot/ArrowCanaria-Llama-8B-SFT-v0.1",
"license:llama3.3",
"endpoints_compatible",
"region:us",
"imatrix",
"conversational"
],
"likes": 4,
"downloads": 2292,
"gated": false,
"private": false,
"last_modified": "2026-03-21T04:41:47.000Z",
"created_at": "2026-03-21T04:15:57.000Z",
"pipeline_tag": "",
"library_name": ""
}
Source payload excerpt (from Hugging Face API)
{
"_id": "69be1b7df363f84d8ff45577",
"id": "mmnga-o/ArrowCanaria-Llama-8B-SFT-v0.1-gguf",
"modelId": "mmnga-o/ArrowCanaria-Llama-8B-SFT-v0.1-gguf",
"sha": "d08186310e1d7c605042c6963deeb135465d7ab6",
"createdAt": "2026-03-21T04:15:57.000Z",
"lastModified": "2026-03-21T04:41:47.000Z",
"author": "mmnga-o",
"downloads": 2292,
"likes": 4,
"gated": false,
"private": false,
"pipeline_tag": "",
"library_name": "",
"siblings_count": 16
}