Instructions to use xCloudinfo/gpt-oss-20b-TAIDE-zhTW-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use xCloudinfo/gpt-oss-20b-TAIDE-zhTW-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="xCloudinfo/gpt-oss-20b-TAIDE-zhTW-GGUF",
	filename="gpt-oss-20b-zhtw.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use xCloudinfo/gpt-oss-20b-TAIDE-zhTW-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 xCloudinfo/gpt-oss-20b-TAIDE-zhTW-GGUF
# Run inference directly in the terminal:
llama cli -hf xCloudinfo/gpt-oss-20b-TAIDE-zhTW-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf xCloudinfo/gpt-oss-20b-TAIDE-zhTW-GGUF
# Run inference directly in the terminal:
llama cli -hf xCloudinfo/gpt-oss-20b-TAIDE-zhTW-GGUF

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 xCloudinfo/gpt-oss-20b-TAIDE-zhTW-GGUF
# Run inference directly in the terminal:
./llama-cli -hf xCloudinfo/gpt-oss-20b-TAIDE-zhTW-GGUF

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 xCloudinfo/gpt-oss-20b-TAIDE-zhTW-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf xCloudinfo/gpt-oss-20b-TAIDE-zhTW-GGUF

Use Docker

docker model run hf.co/xCloudinfo/gpt-oss-20b-TAIDE-zhTW-GGUF

LM Studio
Jan

vLLM

How to use xCloudinfo/gpt-oss-20b-TAIDE-zhTW-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "xCloudinfo/gpt-oss-20b-TAIDE-zhTW-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": "xCloudinfo/gpt-oss-20b-TAIDE-zhTW-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/xCloudinfo/gpt-oss-20b-TAIDE-zhTW-GGUF

Ollama
How to use xCloudinfo/gpt-oss-20b-TAIDE-zhTW-GGUF with Ollama:
```
ollama run hf.co/xCloudinfo/gpt-oss-20b-TAIDE-zhTW-GGUF
```

Unsloth Studio

How to use xCloudinfo/gpt-oss-20b-TAIDE-zhTW-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 xCloudinfo/gpt-oss-20b-TAIDE-zhTW-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 xCloudinfo/gpt-oss-20b-TAIDE-zhTW-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for xCloudinfo/gpt-oss-20b-TAIDE-zhTW-GGUF to start chatting

How to use xCloudinfo/gpt-oss-20b-TAIDE-zhTW-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf xCloudinfo/gpt-oss-20b-TAIDE-zhTW-GGUF

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": "xCloudinfo/gpt-oss-20b-TAIDE-zhTW-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use xCloudinfo/gpt-oss-20b-TAIDE-zhTW-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 xCloudinfo/gpt-oss-20b-TAIDE-zhTW-GGUF

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 xCloudinfo/gpt-oss-20b-TAIDE-zhTW-GGUF

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use xCloudinfo/gpt-oss-20b-TAIDE-zhTW-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf xCloudinfo/gpt-oss-20b-TAIDE-zhTW-GGUF

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 "xCloudinfo/gpt-oss-20b-TAIDE-zhTW-GGUF" \
  --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 xCloudinfo/gpt-oss-20b-TAIDE-zhTW-GGUF with Docker Model Runner:
```
docker model run hf.co/xCloudinfo/gpt-oss-20b-TAIDE-zhTW-GGUF
```

Lemonade

How to use xCloudinfo/gpt-oss-20b-TAIDE-zhTW-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull xCloudinfo/gpt-oss-20b-TAIDE-zhTW-GGUF

Run and chat with the model

lemonade run user.gpt-oss-20b-TAIDE-zhTW-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

gpt-oss-20b-TAIDE-zhTW-GGUF

云碩科技 · xCloudinfo　·　系列：繁中在地化 · TAIDE zh-TW

以 openai/gpt-oss-20b（21B 總參 / 3.6B 活躍 / MoE / MXFP4 / harmony 推理格式）為基底的繁體中文（台灣） reasoning 模型。在程式能力底層之上，用 TAIDE 蒸餾的台灣繁中 self-instruct 指令資料做 LoRA 微調，直接以道地台灣繁中作答。（GGUF，MXFP4，約 14GB）

功能：繁體中文（台灣）問答與寫作——以道地台灣用語回應一般知識、文案、客服、教學等任務。

厲害在哪

道地台灣繁中：用字採台灣慣用（臺灣、臺語、客家話），語氣在地，不是簡轉繁。
疊在程式底層上：以 Code-xCloud 為底再學繁中，保留 reasoning 與 coding 能力。
輕量好部署：MXFP4、約 14GB，本地／離線可跑，資料不外流。

做法

資料：以 TAIDE 蒸餾的台灣繁中 self-instruct 指令資料訓練。

評測成績（繁中・台灣在地知識）

經繁體中文（台灣）知識常識與作答誠實度自動評測：

指標	成績
台灣知識常識 MCQ	86.4%（22 題答對 19）
作答誠實度 probe（不確定時不硬掰、自報不知）	60%（5 題對 3）
綜合分	0.73

滿分類別：交通、制度、地理、常識、氣候、觀光、飲食。
待加強：文化（0/1）、節慶（1/2）、用語（3/4）—— 為後續資料補強的明確方向。
作答誠實度相較純程式版本（40%）提升至 60%：更傾向據實作答、不確定時坦承而非編造。

用法（gpt-oss 是 reasoning 模型，務必加 `--jinja` 套用內建 harmony 模板）

llama.cpp

hf download xCloudinfo/gpt-oss-20b-TAIDE-zhTW-GGUF gpt-oss-20b-zhtw.gguf --local-dir .
llama-server -m gpt-oss-20b-zhtw.gguf --jinja -ngl 999 -c 8192 --host 0.0.0.0 --port 8080

Ollama

printf 'FROM ./gpt-oss-20b-zhtw.gguf\nPARAMETER num_ctx 8192\n' > Modelfile
ollama create gpt-oss-20b-taide-zhtw -f Modelfile && ollama run gpt-oss-20b-taide-zhtw "用一段話介紹台灣，並說說台灣最有名的小吃。"

模型會先思考再輸出最終答案，請給足回覆長度。完整 safetensors 版見對應 repo。

授權與來源聲明

基底：openai/gpt-oss-20b，Apache-2.0。
TAIDE 衍生：訓練資料以 TAIDE 模型蒸餾；使用/重製/改作/散布須遵守 TAIDE 模型授權條款並保留本聲明。
不得用於軍事或非法用途；不得聲稱代表 TAIDE 或國家實驗研究院；須遵守中華民國法律與適用之 EU AI Act。

由云碩科技 xCloudinfo 於自有 AI 算力資源池製作；資料留在本地、流程可重現。

Downloads last month: 675

GGUF

Model size

21B params

Architecture

gpt-oss

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for xCloudinfo/gpt-oss-20b-TAIDE-zhTW-GGUF

Base model

openai/gpt-oss-20b

Quantized

(213)

this model

Collection including xCloudinfo/gpt-oss-20b-TAIDE-zhTW-GGUF

OpenAI gpt-oss · 云碩繁中蒸餾

Collection

基於 OpenAI gpt-oss（120B／20B MoE）的云碩蒸餾模型：繁體中文在地化（TAIDE）與程式碼能力強化，含 Transformers 與 GGUF。 • 10 items • Updated 4 days ago

gpt-oss-20b-TAIDE-zhTW-GGUF

厲害在哪

做法

評測成績（繁中・台灣在地知識）

用法（gpt-oss 是 reasoning 模型，務必加 --jinja 套用內建 harmony 模板）

llama.cpp

Ollama

授權與來源聲明

Model tree for xCloudinfo/gpt-oss-20b-TAIDE-zhTW-GGUF

Collection including xCloudinfo/gpt-oss-20b-TAIDE-zhTW-GGUF

用法（gpt-oss 是 reasoning 模型，務必加 `--jinja` 套用內建 harmony 模板）