Instructions to use roylin1003/royal-zhTW-ID-q3_k_s.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 roylin1003/royal-zhTW-ID-q3_k_s.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 roylin1003/royal-zhTW-ID-q3_k_s.gguf:Q3_K_S
# Run inference directly in the terminal:
llama cli -hf roylin1003/royal-zhTW-ID-q3_k_s.gguf:Q3_K_S

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf roylin1003/royal-zhTW-ID-q3_k_s.gguf:Q3_K_S
# Run inference directly in the terminal:
llama cli -hf roylin1003/royal-zhTW-ID-q3_k_s.gguf:Q3_K_S

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 roylin1003/royal-zhTW-ID-q3_k_s.gguf:Q3_K_S
# Run inference directly in the terminal:
./llama-cli -hf roylin1003/royal-zhTW-ID-q3_k_s.gguf:Q3_K_S

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 roylin1003/royal-zhTW-ID-q3_k_s.gguf:Q3_K_S
# Run inference directly in the terminal:
./build/bin/llama-cli -hf roylin1003/royal-zhTW-ID-q3_k_s.gguf:Q3_K_S

Use Docker

docker model run hf.co/roylin1003/royal-zhTW-ID-q3_k_s.gguf:Q3_K_S

LM Studio
Jan

vLLM

How to use roylin1003/royal-zhTW-ID-q3_k_s.gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "roylin1003/royal-zhTW-ID-q3_k_s.gguf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "roylin1003/royal-zhTW-ID-q3_k_s.gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/roylin1003/royal-zhTW-ID-q3_k_s.gguf:Q3_K_S

Ollama
How to use roylin1003/royal-zhTW-ID-q3_k_s.gguf with Ollama:
```
ollama run hf.co/roylin1003/royal-zhTW-ID-q3_k_s.gguf:Q3_K_S
```

Unsloth Studio

How to use roylin1003/royal-zhTW-ID-q3_k_s.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 roylin1003/royal-zhTW-ID-q3_k_s.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 roylin1003/royal-zhTW-ID-q3_k_s.gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for roylin1003/royal-zhTW-ID-q3_k_s.gguf to start chatting

How to use roylin1003/royal-zhTW-ID-q3_k_s.gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf roylin1003/royal-zhTW-ID-q3_k_s.gguf:Q3_K_S

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": "roylin1003/royal-zhTW-ID-q3_k_s.gguf:Q3_K_S"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use roylin1003/royal-zhTW-ID-q3_k_s.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 roylin1003/royal-zhTW-ID-q3_k_s.gguf:Q3_K_S

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 roylin1003/royal-zhTW-ID-q3_k_s.gguf:Q3_K_S

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use roylin1003/royal-zhTW-ID-q3_k_s.gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf roylin1003/royal-zhTW-ID-q3_k_s.gguf:Q3_K_S

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 "roylin1003/royal-zhTW-ID-q3_k_s.gguf:Q3_K_S" \
  --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 roylin1003/royal-zhTW-ID-q3_k_s.gguf with Docker Model Runner:
```
docker model run hf.co/roylin1003/royal-zhTW-ID-q3_k_s.gguf:Q3_K_S
```

Lemonade

How to use roylin1003/royal-zhTW-ID-q3_k_s.gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull roylin1003/royal-zhTW-ID-q3_k_s.gguf:Q3_K_S

Run and chat with the model

lemonade run user.royal-zhTW-ID-q3_k_s.gguf-Q3_K_S

List all available models

lemonade list

Royal ZhTW-ID Q3_K_S - Quantized Translation Model

高效能量化版本的繁體中文↔印尼文雙向翻譯 GGUF 模型，基於 Llama 架構，採用 Q2_K 量化技術。

模型詳情

格式: GGUF
量化: Q3_K_S (小型混合精度量化)
架構: Llama
大小: ~3.25GB (相較原版 F16 減少約 77% 大小)
語言: 繁體中文 (zh-TW) ↔ 印尼文 (ID) 雙向翻譯
原始模型: roylin1003/royal-zhTW-ID-f16.gguf
量化工具: llama-quantize (llama.cpp)

量化資訊

此模型使用 Q2_K 量化，提供：

極大幅度減少記憶體使用量
適合資源極其有限的環境
非常快的推理速度
在極小模型尺寸下仍保持可用的品質

使用方式

Ollama

ollama run roylin1003/royal-ZhTW-ID-q2_k.gguf

llama.cpp

./main -m royal-ZhTW-ID-q2_k.gguf -p "Hello" -c 2048

Python (llama-cpp-python)

from llama_cpp import Llama
llm = Llama(
    model_path="royal-ZhTW-ID-q2_k.gguf",
    n_ctx=2048,
    n_threads=8
)

LM Studio

直接載入 GGUF 檔案即可使用

翻譯範例

繁體中文 → 印尼文

輸入: 請將以下繁體中文翻譯成印尼文
然而面臨到期債務壓力，可能影響其獲得補助的資格。
輸出: Namun, tekanan dari utang yang jatuh tempo dapat memengaruhi kelayakannya untuk menerima subsidi tersebut.

印尼文 → 繁體中文

輸入: 請將以下印尼文翻譯成繁體中文
Namun, tekanan dari utang yang jatuh tempo dapat memengaruhi kelayakannya untuk menerima subsidi tersebut.
輸出: 然而面臨到期債務壓力，可能影響其獲得補助的資格。

系統需求

RAM: 最低 5GB，建議 7GB+
CPU: 支援 AVX2 指令集
儲存: 約 3.25GB 空間

效能比較

版本	大小	記憶體需求	推理速度	品質保持率
F16	~14GB	~16GB	基準	100%
Q3_K_S	~3.25GB	~5GB	2.5-3x faster	~90%

兼容性

✅ llama.cpp
✅ Ollama
✅ text-generation-webui
✅ LM Studio
✅ KoboldCpp
✅ Jan
✅ GPT4All

量化技術

Q2_K 採用極度壓縮策略：

大幅降低位元精度
優化記憶體存取模式
在極小空間下保持基本翻譯能力

訓練資料

模型基於高品質的中文↔印尼文平行語料進行微調，涵蓋新聞、商務、學術等多種領域的翻譯對。

建議用途

繁體中文↔印尼文雙向翻譯
跨語言文檔處理
商務文件翻譯
新聞文章翻譯
學術文獻翻譯
資源受限環境的翻譯應用

授權

本模型採用 Apache 2.0 授權條款。

致謝

感謝 llama.cpp 團隊提供優秀的量化工具。

由 Roy Lin 創建 🚀 | Q3_K_S 小型量化版本

Downloads last month: 26

GGUF

Model size

8B params

Architecture

qwen2

Hardware compatibility

3-bit