Instructions to use twinkle-ai/Llama-3.2-3B-F1-Reasoning-Instruct-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use twinkle-ai/Llama-3.2-3B-F1-Reasoning-Instruct-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="twinkle-ai/Llama-3.2-3B-F1-Reasoning-Instruct-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("twinkle-ai/Llama-3.2-3B-F1-Reasoning-Instruct-GGUF", dtype="auto")

llama-cpp-python

How to use twinkle-ai/Llama-3.2-3B-F1-Reasoning-Instruct-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="twinkle-ai/Llama-3.2-3B-F1-Reasoning-Instruct-GGUF",
	filename="Llama-3.2-3B-F1-Reasoning-Instruct-BF16.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 twinkle-ai/Llama-3.2-3B-F1-Reasoning-Instruct-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf twinkle-ai/Llama-3.2-3B-F1-Reasoning-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf twinkle-ai/Llama-3.2-3B-F1-Reasoning-Instruct-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf twinkle-ai/Llama-3.2-3B-F1-Reasoning-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf twinkle-ai/Llama-3.2-3B-F1-Reasoning-Instruct-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 twinkle-ai/Llama-3.2-3B-F1-Reasoning-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf twinkle-ai/Llama-3.2-3B-F1-Reasoning-Instruct-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 twinkle-ai/Llama-3.2-3B-F1-Reasoning-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf twinkle-ai/Llama-3.2-3B-F1-Reasoning-Instruct-GGUF:Q4_K_M

Use Docker

docker model run hf.co/twinkle-ai/Llama-3.2-3B-F1-Reasoning-Instruct-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use twinkle-ai/Llama-3.2-3B-F1-Reasoning-Instruct-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "twinkle-ai/Llama-3.2-3B-F1-Reasoning-Instruct-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": "twinkle-ai/Llama-3.2-3B-F1-Reasoning-Instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/twinkle-ai/Llama-3.2-3B-F1-Reasoning-Instruct-GGUF:Q4_K_M

SGLang

How to use twinkle-ai/Llama-3.2-3B-F1-Reasoning-Instruct-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "twinkle-ai/Llama-3.2-3B-F1-Reasoning-Instruct-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "twinkle-ai/Llama-3.2-3B-F1-Reasoning-Instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "twinkle-ai/Llama-3.2-3B-F1-Reasoning-Instruct-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "twinkle-ai/Llama-3.2-3B-F1-Reasoning-Instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use twinkle-ai/Llama-3.2-3B-F1-Reasoning-Instruct-GGUF with Ollama:
```
ollama run hf.co/twinkle-ai/Llama-3.2-3B-F1-Reasoning-Instruct-GGUF:Q4_K_M
```

Unsloth Studio

How to use twinkle-ai/Llama-3.2-3B-F1-Reasoning-Instruct-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 twinkle-ai/Llama-3.2-3B-F1-Reasoning-Instruct-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 twinkle-ai/Llama-3.2-3B-F1-Reasoning-Instruct-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for twinkle-ai/Llama-3.2-3B-F1-Reasoning-Instruct-GGUF to start chatting

How to use twinkle-ai/Llama-3.2-3B-F1-Reasoning-Instruct-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf twinkle-ai/Llama-3.2-3B-F1-Reasoning-Instruct-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": "twinkle-ai/Llama-3.2-3B-F1-Reasoning-Instruct-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use twinkle-ai/Llama-3.2-3B-F1-Reasoning-Instruct-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf twinkle-ai/Llama-3.2-3B-F1-Reasoning-Instruct-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 twinkle-ai/Llama-3.2-3B-F1-Reasoning-Instruct-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use twinkle-ai/Llama-3.2-3B-F1-Reasoning-Instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/twinkle-ai/Llama-3.2-3B-F1-Reasoning-Instruct-GGUF:Q4_K_M
```

Lemonade

How to use twinkle-ai/Llama-3.2-3B-F1-Reasoning-Instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull twinkle-ai/Llama-3.2-3B-F1-Reasoning-Instruct-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Llama-3.2-3B-F1-Reasoning-Instruct-GGUF-Q4_K_M

List all available models

lemonade list

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Model Card for Llama-3.2-3B-F1-Reasoning-Instruct (a.k.a Formosa-1-Reasoning or F1-Reasoning)

Llama-3.2-3B-F1-Reasoning-Instruct（a.k.a Formosa-1-Reasoning or F1-Reasoning）是由 Twinkle AI 與 APMIC 合作開發，並在國家高速網路與計算中心技術指導之下，針對中華民國台灣語境與任務需求所微調之繁體中文語言模型，涵蓋法律、教育、生活應用等多元場景，並以高指令跟隨能力為目標進行強化。

Model Details

Model Description

Developed by: Liang Hsun Huang、Min Yi Chen、Wen Bin Lin、Chao Chun Chuang & Dave Sung (All authors have contributed equally to this work.)
Funded by: APMIC
Model type: LlamaForCausalLM
Language(s) (NLP): Tranditional Chinese & English
License: llama3.2

Model Sources

Repository: twinkle-ai/Llama-3.2-3B-F1-Reasoning-Instruct
Paper: (TBA)
Demo: Playground

Evaluation

Results

下表採用 🌟 Twinkle Eval 評測框架

模型	評測模式	TMMLU+(%)	台灣法律(%)	MMLU(%)	測試次數	選項排序
mistralai/Mistral-Small-24B-Instruct-2501	box	56.15 (±0.0172)	37.48 (±0.0098)	74.61 (±0.0154)	3	隨機
meta-llama/Llama-3.2-3B-Instruct	box	15.49 (±0.0104)	25.68 (±0.0200)	6.90 (±0.0096)	3	隨機
meta-llama/Llama-3.2-3B-Instruct	pattern	35.85 (±0.0174)	32.22 (±0.0023)	59.33 (±0.0168)	3	隨機
MediaTek-Research/Llama-Breeze2-3B-Instruct	pattern	40.32 (±0.0181)	38.92 (±0.0193)	55.37 (±0.0180)	3	隨機
🌟 twinkle-ai/Llama-3.2-3B-F1-Reasoning-Instruct (ours)	box	46.16 (±0.0198)	34.92 (±0.0243)	51.22 (±0.0206)	3	隨機

下表用 lighteval 評測框架

模型	MATH-500	GPQA Diamond
meta-llama/Llama-3.2-3B-Instruct	44.40	27.78
🌟 twinkle-ai/Llama-3.2-3B-F1-Reasoning-Instruct (ours)	51.40	33.84

Use this model

vLLM

vllm serve twinkle-ai/Llama-3.2-3B-F1-Reasoning-Instruct \
  --port 8001 \
  --enable-reasoning \
  --reasoning-parser deepseek_r1 \
  --enable-auto-tool-choice \
  --tool-call-parser hermes

Ollama

ollama run TwinkleAI/Llama-3.2-3B-F1-Resoning-Instruct

LM Studio

請在 My Models 中找到你要使用的模型，點選 ⚙️ Edit model default config。進入後，切換到 Prompt 頁籤，將原有的 Prompt Template 內容清空，並貼上以下提供的內容：

{% if bos_token is defined %}{{ bos_token }}{% endif %}
<|start_header_id|>system<|end_header_id|>

{% set first_is_system = messages|length > 0 and messages[0].role == 'system' %}
{% set has_tools = tools and tools|length > 0 %}

{% if not has_tools and first_is_system %}
{{ messages[0].content }}

{% elif has_tools and first_is_system %}
{{ messages[0].content }}

{% elif has_tools and not first_is_system %}
You are a function calling AI model.
{% endif %}

{% if tools and tools|length > 0 %}
You are provided with function signatures within <tools> </tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools:

<tools>
[
{% for t in tools %}
  {% set f = t.function if t.function is defined else t %}
  {
    "type": "function",
    "function": {
      "name": "{{ f.name }}",
      "description": "{{ f.description }}",
      "parameters": {{ f.parameters | tojson }}
    }
  }{% if not loop.last %},{% endif %}
{% endfor %}
]
</tools>

For each function call return a json object with function name and arguments within <tool_call> </tool_call> tags with the following schema:
<tool_call>
{"name": &lt;function-name&gt;, "arguments": &lt;args-dict&gt;}
</tool_call>
{% endif %}<|eot_id|>

{% for m in messages %}
{% if not (loop.first and m.role == 'system') %}
  {% if m.role == 'user' %}
<|start_header_id|>user<|end_header_id|>

{{ m.content }}<|eot_id|>

  {% elif m.role == 'assistant' %}
<|start_header_id|>assistant<|end_header_id|>

    {% if m.tool_calls is defined and m.tool_calls %}
      {% for tc in m.tool_calls %}
        {% if tc.function is defined %}
<tool_call>
{"name": "{{ tc.function.name }}", "arguments": {{ tc.function.arguments | tojson }}}
</tool_call>
        {% else %}
<tool_call>
{"name": "{{ tc.name }}", "arguments": {{ tc.arguments | tojson }}}
</tool_call>
        {% endif %}
      {% endfor %}
    {% else %}
{{ m.content }}
    {% endif %}<|eot_id|>

  {% elif m.role == 'tool' %}
<|start_header_id|>ipython<|end_header_id|>

<tool_response>
{{ m.content }}
</tool_response><|eot_id|>
  {% endif %}
{% endif %}
{% endfor %}

{% if add_generation_prompt %}
<|start_header_id|>assistant<|end_header_id|>

{% endif %}

🔧 Tool Calling

本模型使用 Hermes 格式訓練，並支援平行呼叫（Parallel calling），以下為完整範例流程。 Tool call 模板已經為大家寫好放進 chat-template 了，Enjoy it！

1️⃣ 啟動 vLLM 後端

⚠️ 注意：需要 vLLM 版本 >= 0.8.3，否則 enable-reasoning、enable-auto-tool-choice 無法同時開啟

vllm serve twinkle-ai/Llama-3.2-3B-F1-Reasoning-Instruct \
  --port 8001 \
  --enable-reasoning \
  --reasoning-parser deepseek_r1 \
  --enable-auto-tool-choice \
  --tool-call-parser hermes

2️⃣ 定義工具（Functions）

def get_weather(location: str, unit: str):
    return f"{location}的氣溫是{unit}26度，晴朗無風"

def search(query: str):
    return "川普終於宣布對等關稅政策，針對 18 個經濟體課徵一半的對等關稅，並從 4/5 起對所有進口產品徵收10%的基準關稅！美國將針對被認定為不當貿易行為(不公平貿易) 的國家，於 4/9 起課徵報復型對等關稅 (Discounted Reciprocal Tariff)，例如：日本將被課徵 24% 的關稅，歐盟則為 20%，以取代普遍性的 10% 關稅。\n針對中國則開啟新一波 34% 關稅，並疊加於先前已實施的關稅上，這將使中國進口商品的基本關稅稅率達到 54%，而且這尚未包含拜登總統任內或川普第一任期所施加的額外關稅。加拿大與墨西哥則不適用這套對等關稅制度，但川普認為這些國家在芬太尼危機與非法移民問題尚未完全解決，因此計畫對這兩國的大多數進口商品施加 25% 關稅。另外原本針對汽車與多數其他商品的關稅豁免將於 4/2 到期。\n台灣的部分，美國擬向台灣課徵32％的對等關稅，雖然並未針對晶片特別課徵關稅，但仍在記者會中提到台灣搶奪所有的電腦與半導體晶片，最終促成台積電對美國投資計劃額外加碼 1,000 億美元的歷史性投資；歐盟則課徵20％的對等關稅。最後是汽車關稅將於 4/2 起，對所有外國製造的汽車課徵25% 關稅。"

tools = [
    {
        "type": "function",
        "function": {
            "name": "get_weather",
            "description": "Get the current weather in a given location",
            "parameters": {
                "type": "object",
                "properties": {
                    "location": {"type": "string", "description": "國家或城市名, e.g., 'Taipei'、'Jaipei'"},
                    "unit": {"type": "string", "description": "氣溫單位，亞洲城市使用攝氏；歐美城市使用華氏", "enum": ["celsius", "fahrenheit"]}
                },
                "required": ["location", "unit"]
            }
        }
    },
    {
        "type": "function",
        "function": {
            "name": "search",
            "description": "這是一個類似 Google 的搜尋引擎，關於知識、天氣、股票、電影、小說、百科等等問題，如果你不確定答案就搜尋一下。",
            "parameters": {
                "type": "object",
                "properties": {
                    "query": {"type": "string", "description": "should be a search query, e.g., '2024 南韓 戒嚴'"}
                },
                "required": ["query"]
            }
        }
    }
]

3️⃣ 執行工具調用（Tool Calls）

⚠️ 注意：system_prompt 可以不用帶，除非是需要時間基準的工具。

response = client.chat.completions.create(
    model=client.models.list().data[0].id,
    messages=[
        {"role": "system", "content": "記住你的知識截止於 2024/12，今天是 2025/4/7"},
        {"role": "user", "content": "台北氣溫如何? 另外，告訴我川普最新關稅政策"},
    ],
    max_tokens=1500,
    temperature=0.6,
    top_p=0.95,
    tools=tools,
    tool_choice="auto"
)

print(response.choices[0].message.reasoning_content)
print(response.choices[0].message.tool_calls)

🧠 推理內容輸出（僅顯示部分）

好的，我需要幫助這個使用者解決他們的問題。他們問了兩件事：首先，臺北市的天氣情況，以及第二，關於川普最近的關稅政策。
對於第一部分，他們提到了“臺北”，所以應該呼叫 get_weather 函式…
接下來是關於川普的新關稅政策…
總結一下，我需要分別進行兩次 API 呼叫，每次都有各自正確填寫的參數…

⚙️ Tool Calls List

[ChatCompletionMessageToolCall(id='chatcmpl-tool-35e74420119349999913a10133b84bd3', function=Function(arguments='{"location": "Taipei", "unit": "celsius"}', name='get_weather'), type='function'), ChatCompletionMessageToolCall(id='chatcmpl-tool-7ffdcb98e59f4134a6171defe7f2e31b', function=Function(arguments='{"query": "Donald Trump latest tariffs policy"}', name='search'), type='function')]

4️⃣ 產生最終回答

response = client.chat.completions.create(
    model=client.models.list().data[0].id,
    messages=[
        {"role": "system", "content": "記住你的知識截止於 2024/12，今天是 2025/4/7"},
        {"role": "user", "content": "台北氣溫如何? 另外，告訴我川普最新關稅政策"},
        {
            "role": "assistant",
            "content": "",
            "tool_calls": [
                {
                    "id": response.choices[0].message.tool_calls[0].id,
                    "type": "function",
                    "function": {
                        "name": response.choices[0].message.tool_calls[0].function.name,
                        "arguments": response.choices[0].message.tool_calls[0].function.arguments
                    }
                },
                {
                    "id": response.choices[0].message.tool_calls[1].id,
                    "type": "function",
                    "function": {
                        "name": response.choices[0].message.tool_calls[1].function.name,
                        "arguments": response.choices[0].message.tool_calls[1].function.arguments
                    }
                }
            ]
        },
        {
            "role": "tool",
            "content": search(**json.loads(response.choices[0].message.tool_calls[0].function.arguments)),
            "tool_call_id": response.choices[0].message.tool_calls[0].id # tool_call_id 必須要帶，才能正確配對 工具 及 tool_call
        },
        {
            "role": "tool",
            "content": get_weather(**json.loads(response.choices[0].message.tool_calls[1].function.arguments)),
            "tool_call_id": response.choices[0].message.tool_calls[1].id # tool_call_id 必須要帶，才能正確配對 工具 及 tool_call
        }
    ],
    max_tokens=1500,
    temperature=0.6,
    top_p=0.95,
    tools=tools,
    tool_choice="auto"
)

print(response.choices[0].message.reasoning_content)
print(response.choices[0].message.content)

🧠 推理內容輸出（僅顯示部分）

首先，我需要處理使用者的查詢，他們要求了解臺北市的當下氣溫以及川普最近的關稅政策…
在呼叫了 get_weather 後得到了臺北市氣溫為 26 度（攝氏）…
接著，使用 search 搜尋「川普最新關稅政策 2025」…
整合後，我提供如下摘要：

📋 最終輸出內容

以下是您請求的資訊：

**臺北市氣溫**
- 目前的氣溫為 **26°C**（攝氏）
- 天候狀況：晴朗無風

**川普最新關稅政策概述**
1. **對等關稅政策**  
   - 對 18 個經濟體課徵 50% 的對等關稅  
   - 自 4 月 5 日起，所有進口產品全面徵收 10% 基本關稅  

2. **報復型對等關稅**  
   - 日本 24%、歐盟 20%  

3. **對中國的高額關稅**  
   - 增加至 54%（原有關稅 + 新增 34%）  

4. **特殊案例**  
   - 加拿大與墨西哥不適用，但其他商品課徵 25%  
   - 汽車與部分商品的免稅即將到期  

5. **對台灣的影響**  
   - 美國計畫對台灣課徵 32% 關稅，但晶片暫無額外課稅  

6. **全球視角**  
   - 歐盟與日本關稅比例相對較高

Citation

@misc{twinkleai2025llama3.2f1,
  title        = {Llama-3.2-3B-F1-Reasoning-Instruct: A Traditional Chinese Instruction-Tuned Reasoning Language Model for Taiwan},
  author       = {Huang, Liang Hsun and Chen, Min Yi and Lin, Wen Bin and Chuang, Chao Chun and Sung, Dave},
  year         = {2025},
  howpublished = {\url{https://huggingface.co/twinkle-ai/Llama-3.2-3B-F1-Instruct}},
  note         = {Twinkle AI and APMIC. All authors contributed equally.}
}