Instructions to use tokimoa/jp-gijiroku-qwen3-4b-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use tokimoa/jp-gijiroku-qwen3-4b-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf tokimoa/jp-gijiroku-qwen3-4b-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf tokimoa/jp-gijiroku-qwen3-4b-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf tokimoa/jp-gijiroku-qwen3-4b-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf tokimoa/jp-gijiroku-qwen3-4b-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf tokimoa/jp-gijiroku-qwen3-4b-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf tokimoa/jp-gijiroku-qwen3-4b-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf tokimoa/jp-gijiroku-qwen3-4b-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tokimoa/jp-gijiroku-qwen3-4b-GGUF:Q4_K_M

Use Docker

docker model run hf.co/tokimoa/jp-gijiroku-qwen3-4b-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use tokimoa/jp-gijiroku-qwen3-4b-GGUF with Ollama:
```
ollama run hf.co/tokimoa/jp-gijiroku-qwen3-4b-GGUF:Q4_K_M
```

Unsloth Studio

How to use tokimoa/jp-gijiroku-qwen3-4b-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for tokimoa/jp-gijiroku-qwen3-4b-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for tokimoa/jp-gijiroku-qwen3-4b-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for tokimoa/jp-gijiroku-qwen3-4b-GGUF to start chatting

How to use tokimoa/jp-gijiroku-qwen3-4b-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf tokimoa/jp-gijiroku-qwen3-4b-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "tokimoa/jp-gijiroku-qwen3-4b-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use tokimoa/jp-gijiroku-qwen3-4b-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf tokimoa/jp-gijiroku-qwen3-4b-GGUF:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "tokimoa/jp-gijiroku-qwen3-4b-GGUF:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use tokimoa/jp-gijiroku-qwen3-4b-GGUF with Docker Model Runner:
```
docker model run hf.co/tokimoa/jp-gijiroku-qwen3-4b-GGUF:Q4_K_M
```

Lemonade

How to use tokimoa/jp-gijiroku-qwen3-4b-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tokimoa/jp-gijiroku-qwen3-4b-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.jp-gijiroku-qwen3-4b-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use tokimoa/jp-gijiroku-qwen3-4b-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf tokimoa/jp-gijiroku-qwen3-4b-GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default tokimoa/jp-gijiroku-qwen3-4b-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

jp-gijiroku-qwen3-4b-GGUF

File size: 2,803 Bytes

---
license: apache-2.0
base_model: Qwen/Qwen3-4B-Instruct-2507
language:
  - ja
tags:
  - gguf
  - llama.cpp
  - japanese
  - meeting-minutes
  - gijiroku
---

# jp-gijiroku-qwen3-4b-GGUF

> **後継版があります**: 実際の60分Zoom会議で見つけた弱点（日付捏造・完了報告の決定混入・期限誤借用・話者ラベル転写・報告内コミット宿題）を標的に継続学習した [jp-gijiroku-qwen3-4b-v2-GGUF](https://huggingface.co/tokimoa/jp-gijiroku-qwen3-4b-v2-GGUF) を公開しました。新規利用はv2を推奨します。

音声文字起こし由来の崩れた入力に強い日本語議事録抽出モデル [jp-gijiroku-qwen3-4b](https://huggingface.co/tokimoa/jp-gijiroku-qwen3-4b) のGGUF版です。llama.cppでWindows/Linux/MacのCPU・GPUで動きます。Ollamaなら `ollama run tokimoa/jp-gijiroku-4b` です。

## ファイルと実測（ASR劣化転写20件・全項目正解率）

| ファイル | サイズ | 全項目正解 | 備考 |
|---|---|---|---|
| **Q8_0** | 4.0GB | **16/20** | MLX版と完全同値 |
| Q4_K_M | 2.3GB | 19/20 | 省メモリ。この検証ではQ8_0より高値（n=20の揺らぎ圏・同帯域） |
| f16 | 7.5GB | — | 参照用 |

比較: 公開中の1.7B版は同条件12/20です。整った議事メモには高速な [jp-minutes-extractor-1.7b-GGUF](https://huggingface.co/tokimoa/jp-minutes-extractor-1.7b-GGUF) で十分です。

## 使い方

```bash
llama-server -m jp-gijiroku-qwen3-4b-Q8_0.gguf --port 8080 --jinja --reasoning-format none -c 8192
```

- **`--reasoning-format none` を推奨します。** 既定パーサだと判断過程がreasoning_content側に分離されcontentが空になる場合があります
- 出力は「判断過程 → 最終行にJSON」です。**最終行をパース**してください（スキーマ: `{"date", "attendees", "decisions", "todos": [{"task","owner","due"}], "next_meeting"}`）
- プロンプトは定型文「次の議事録から出席者・決定事項・宿題（担当と期限）・次回予定を抽出してJSONで出力してください。」+ 本文をそのまま使ってください（学習分布の形式）
- 本文に日付が含まれない場合、dateフィールドは不定です（学習データは常に日付を含むため）

## データと帰属

- 学習データ: 合成会議（正解既知・ASR劣化込み）に対する [DeepSeek-V4-Flash](https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731) の検証済み解答軌跡（利用規約は蒸留を明示的に許可）
- ベース: [Qwen/Qwen3-4B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507)（Apache-2.0）

---
Developed by [tokimoa](https://tokimoa.jp) — データを外に出さないAI活用を支援しています