Instructions to use suyu-io/Llama-3.1-8B-Thinking-Distill-R1-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 suyu-io/Llama-3.1-8B-Thinking-Distill-R1-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 suyu-io/Llama-3.1-8B-Thinking-Distill-R1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf suyu-io/Llama-3.1-8B-Thinking-Distill-R1-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 suyu-io/Llama-3.1-8B-Thinking-Distill-R1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf suyu-io/Llama-3.1-8B-Thinking-Distill-R1-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 suyu-io/Llama-3.1-8B-Thinking-Distill-R1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf suyu-io/Llama-3.1-8B-Thinking-Distill-R1-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 suyu-io/Llama-3.1-8B-Thinking-Distill-R1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf suyu-io/Llama-3.1-8B-Thinking-Distill-R1-GGUF:Q4_K_M

Use Docker

docker model run hf.co/suyu-io/Llama-3.1-8B-Thinking-Distill-R1-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use suyu-io/Llama-3.1-8B-Thinking-Distill-R1-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "suyu-io/Llama-3.1-8B-Thinking-Distill-R1-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": "suyu-io/Llama-3.1-8B-Thinking-Distill-R1-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/suyu-io/Llama-3.1-8B-Thinking-Distill-R1-GGUF:Q4_K_M

Ollama
How to use suyu-io/Llama-3.1-8B-Thinking-Distill-R1-GGUF with Ollama:
```
ollama run hf.co/suyu-io/Llama-3.1-8B-Thinking-Distill-R1-GGUF:Q4_K_M
```

Unsloth Studio

How to use suyu-io/Llama-3.1-8B-Thinking-Distill-R1-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 suyu-io/Llama-3.1-8B-Thinking-Distill-R1-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 suyu-io/Llama-3.1-8B-Thinking-Distill-R1-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for suyu-io/Llama-3.1-8B-Thinking-Distill-R1-GGUF to start chatting

How to use suyu-io/Llama-3.1-8B-Thinking-Distill-R1-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf suyu-io/Llama-3.1-8B-Thinking-Distill-R1-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": "suyu-io/Llama-3.1-8B-Thinking-Distill-R1-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use suyu-io/Llama-3.1-8B-Thinking-Distill-R1-GGUF with Docker Model Runner:
```
docker model run hf.co/suyu-io/Llama-3.1-8B-Thinking-Distill-R1-GGUF:Q4_K_M
```

Lemonade

How to use suyu-io/Llama-3.1-8B-Thinking-Distill-R1-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull suyu-io/Llama-3.1-8B-Thinking-Distill-R1-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Llama-3.1-8B-Thinking-Distill-R1-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use suyu-io/Llama-3.1-8B-Thinking-Distill-R1-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 suyu-io/Llama-3.1-8B-Thinking-Distill-R1-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 suyu-io/Llama-3.1-8B-Thinking-Distill-R1-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use suyu-io/Llama-3.1-8B-Thinking-Distill-R1-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf suyu-io/Llama-3.1-8B-Thinking-Distill-R1-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 "suyu-io/Llama-3.1-8B-Thinking-Distill-R1-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"

Llama-3.1-8B-Thinking-Distill-R1-GGUF

模型简介

本模型基于 meta-llama/Llama-3.1-8B 进行微调训练，使用满血版 DeepSeek-R1 蒸馏的中文数据集进行训练，使模型具备深度思考（Thinking）能力，同时显著提升了中文理解和推理能力。

主要特点

🧠 深度思考模式：相较于原版 Llama-3.1-8B，新增了深度思考能力，能够进行更复杂的推理
🇨🇳 中文能力增强：通过中文蒸馏数据集训练，大幅提升中文理解和生成能力
💾 轻量化部署：Q4_K_M 量化版本，内存占用极小，适合本地部署
⚡ 高效训练：使用 Unsloth 实现 2 倍训练加速

训练数据

训练集和验证集使用 Congliu/Chinese-DeepSeek-R1-Distill-data-110k，这是一个开源的中文 DeepSeek-R1 蒸馏数据集。

数据分布

类别	样本数量	说明
Math	36,568	数学推理题目
Exam	2,432	考试题目
STEM	12,648	科学、技术、工程、数学相关
General	58,352	包含弱智吧、逻辑推理、小红书、知乎、Chat 等多样化内容
总计	110,000	-

使用方法

llama.cpp

文本生成：

./llama.cpp/llama-cli -hf suyu-io/Llama-3.1-8B-Thinking-Distill-R1-GGUF --jinja

多模态模型：

./llama.cpp/llama-mtmd-cli -hf suyu-io/Llama-3.1-8B-Thinking-Distill-R1-GGUF --jinja

Ollama

本仓库包含 Ollama Modelfile，可直接用于部署。

可用模型文件

文件名	量化方式	说明
`Meta-Llama-3.1-8B-Instruct.Q4_K_M.gguf`	Q4_K_M	4-bit 量化，平衡质量与大小

模型信息

基础模型: meta-llama/Llama-3.1-8B
训练数据: Congliu/Chinese-DeepSeek-R1-Distill-data-110k
量化格式: GGUF (Q4_K_M)
训练框架: Unsloth

适用场景

中文问答与对话
数学推理与计算
逻辑推理任务
STEM 领域问题解答
通用中文文本生成

致谢

Meta AI - Llama 3.1 基础模型
DeepSeek - R1 模型蒸馏数据
Unsloth - 高效训练框架
Congliu - 中文蒸馏数据集

Downloads last month: 42

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

4-bit

Model tree for suyu-io/Llama-3.1-8B-Thinking-Distill-R1-GGUF

Base model

meta-llama/Llama-3.1-8B

Quantized

(326)

this model

suyu-io
/

Llama-3.1-8B-Thinking-Distill-R1-GGUF

Llama-3.1-8B-Thinking-Distill-R1-GGUF

模型简介

主要特点

训练数据

数据分布

使用方法

llama.cpp

Ollama

可用模型文件

模型信息

适用场景

致谢

Model tree for suyu-io/Llama-3.1-8B-Thinking-Distill-R1-GGUF

Dataset used to train suyu-io/Llama-3.1-8B-Thinking-Distill-R1-GGUF