Instructions to use Luckybalabala/AutoGLM-Phone-9B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Luckybalabala/AutoGLM-Phone-9B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Luckybalabala/AutoGLM-Phone-9B-GGUF",
	filename="AutoGLM-Phone-9B-Q2_K.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": [
				{
					"type": "text",
					"text": "Describe this image in one sentence."
				},
				{
					"type": "image_url",
					"image_url": {
						"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
					}
				}
			]
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Luckybalabala/AutoGLM-Phone-9B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Luckybalabala/AutoGLM-Phone-9B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Luckybalabala/AutoGLM-Phone-9B-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 Luckybalabala/AutoGLM-Phone-9B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Luckybalabala/AutoGLM-Phone-9B-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 Luckybalabala/AutoGLM-Phone-9B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Luckybalabala/AutoGLM-Phone-9B-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 Luckybalabala/AutoGLM-Phone-9B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Luckybalabala/AutoGLM-Phone-9B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Luckybalabala/AutoGLM-Phone-9B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use Luckybalabala/AutoGLM-Phone-9B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Luckybalabala/AutoGLM-Phone-9B-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": "Luckybalabala/AutoGLM-Phone-9B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/Luckybalabala/AutoGLM-Phone-9B-GGUF:Q4_K_M

Ollama
How to use Luckybalabala/AutoGLM-Phone-9B-GGUF with Ollama:
```
ollama run hf.co/Luckybalabala/AutoGLM-Phone-9B-GGUF:Q4_K_M
```

Unsloth Studio new

How to use Luckybalabala/AutoGLM-Phone-9B-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 Luckybalabala/AutoGLM-Phone-9B-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 Luckybalabala/AutoGLM-Phone-9B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Luckybalabala/AutoGLM-Phone-9B-GGUF to start chatting

Docker Model Runner
How to use Luckybalabala/AutoGLM-Phone-9B-GGUF with Docker Model Runner:
```
docker model run hf.co/Luckybalabala/AutoGLM-Phone-9B-GGUF:Q4_K_M
```

Lemonade

How to use Luckybalabala/AutoGLM-Phone-9B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Luckybalabala/AutoGLM-Phone-9B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.AutoGLM-Phone-9B-GGUF-Q4_K_M

List all available models

lemonade list

AutoGLM-Phone-9B GGUF 量化模型集合

这是 AutoGLM-Phone-9B 模型的完整 GGUF 量化版本集合，专门为手机自动化任务优化。

🎯 模型简介

AutoGLM-Phone-9B 是基于 GLM-4V-9B 的多模态视觉语言模型，专门针对手机自动化场景进行了优化。该模型能够理解手机屏幕截图并生成相应的操作指令。

📦 可用的量化版本

量化类型	文件大小	内存需求	推荐用途	下载链接
Q2_K	3.73 GB	~4 GB	极限内存环境	下载
Q3_K_S	4.28 GB	~5 GB	低内存设备	下载
Q3_K_M	4.63 GB	~5 GB	平衡性能/内存	下载
Q3_K_L	4.84 GB	~6 GB	稍好质量	下载
Q4_0	5.08 GB	~6 GB	传统4位量化	下载
Q4_1	5.60 GB	~6 GB	改进4位量化	下载
Q4_K_S	5.36 GB	~6 GB	推荐-小显卡	下载
Q4_K_M	5.74 GB	~7 GB	推荐-平衡 ⭐	下载
Q5_0	6.11 GB	~7 GB	传统5位量化	下载
Q5_1	6.62 GB	~8 GB	改进5位量化	下载
Q5_K_S	6.24 GB	~7 GB	高质量-小	下载
Q5_K_M	6.57 GB	~8 GB	高质量-中	下载
Q6_K	7.70 GB	~9 GB	接近原始质量	下载
Q8_0	9.31 GB	~11 GB	最高质量	下载
F16	17.52 GB	~20 GB	原始精度	下载

🚀 快速开始

使用 llama.cpp

# 下载模型和视觉投影器
wget https://huggingface.co/Luckybalabala/AutoGLM-Phone-9B-Q4_K_M.gguf/resolve/main/AutoGLM-Phone-9B-Q4_K_M.gguf
wget https://huggingface.co/Luckybalabala/AutoGLM-Phone-9B-Q4_K_M.gguf/resolve/main/AutoGLM-Phone-9B-mmproj.gguf

# 启动服务器
./llama-server -m AutoGLM-Phone-9B-Q4_K_M.gguf --mmproj AutoGLM-Phone-9B-mmproj.gguf --host 0.0.0.0 --port 8080

与 Open-AutoGLM 集成

# 克隆 Open-AutoGLM 项目
git clone https://github.com/OpenBMB/AutoGLM.git
cd AutoGLM

# 配置模型 API
python main.py --base-url http://localhost:8080/v1

💻 系统要求

最低要求

操作系统: Windows 10/11, Linux, macOS
内存: 8GB+ RAM
存储: 根据选择的量化版本

🔧 技术细节

基础模型: THUDM/glm-4v-9b
量化工具: llama.cpp quantize
支持格式: GGUF
多模态: 支持图像+文本输入
API: OpenAI 兼容接口

📊 性能对比

量化类型	推理速度	内存占用	质量保持	推荐场景
Q2_K	最快	最低	70%	资源受限
Q4_K_M	快	中等	85%	平衡推荐
Q6_K	中等	较高	95%	高质量需求
Q8_0	较慢	高	98%	最佳质量

🔗 相关资源

原项目: Open-AutoGLM
llama.cpp: GitHub
演示视频: B站演示
技术博客: AutoGLM 集成指南

📝 使用许可

本模型遵循 Apache 2.0 许可证。请查看原始模型的许可证条款。

⚠️ 注意事项

模型用途: 专门用于手机自动化任务，其他用途效果可能不佳
安全提醒: 请在受控环境中测试，避免在重要设备上直接使用
性能差异: 不同量化级别的性能和质量存在差异，请根据需求选择
更新频率: 模型会根据 Open-AutoGLM 项目更新而更新

🤝 贡献

欢迎提交 Issue 和建议来改进这个模型集合。

标签: GLM-4V 多模态 手机自动化 GGUF 量化模型 llama.cpp

Downloads last month: 498

GGUF

Model size

9B params

Architecture

glm4

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

View +1 variant

Model tree for Luckybalabala/AutoGLM-Phone-9B-GGUF

Base model

zai-org/glm-4v-9b

Quantized

(5)

this model

Luckybalabala
/

AutoGLM-Phone-9B-GGUF