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

Libraries

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

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="BlcaCola/AutoGLM-Phone-9B-GGUF",
	filename="AutoGLM-Phone-9B-F16.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 BlcaCola/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 BlcaCola/AutoGLM-Phone-9B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf BlcaCola/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 BlcaCola/AutoGLM-Phone-9B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf BlcaCola/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 BlcaCola/AutoGLM-Phone-9B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf BlcaCola/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 BlcaCola/AutoGLM-Phone-9B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf BlcaCola/AutoGLM-Phone-9B-GGUF:Q4_K_M

Use Docker

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

LM Studio
Jan

vLLM

How to use BlcaCola/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 "BlcaCola/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": "BlcaCola/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/BlcaCola/AutoGLM-Phone-9B-GGUF:Q4_K_M

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

Unsloth Studio new

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

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

Lemonade

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

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull BlcaCola/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 Quantized Model Collection/AutoGLM-Phone-9B GGUF 量化模型集合

Congratulations! This is the most complete and fully usable collection of AutoGLM-Phone-9B model GGUF quantized versions you can find.🎉🎉🎉
恭喜你！这是你能找到最完整，并且绝对可用的 AutoGLM-Phone-9B 模型 GGUF 量化版本集合。🎉🎉🎉

Model Introduction/模型简介

Phone Agent is a mobile intelligent assistant framework built on AutoGLM, capable of understanding smartphone screens through multimodal perception and executing automated operations to complete tasks.
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。

⚠️Please note! This is a multimodal vision language model, so in addition to the model itself, you also need the mmproj file. Please be sure to download this file for use!
⚠️请注意！这是多模态视觉语言模型，所以除了模型本身，你还需要mmproj文件，请务必下载这个文件一起使用！

Available quantization versions/可用的量化版本

Quantization Type	Size	Memory Requirement	Notes	Download Link
Q2_K	3.73 GB	~4 GB	Not recommended 不推荐	Download
Q3_K_S	4.28 GB	~5 GB	Not recommended 不推荐	Download
Q3_K_M	4.63 GB	~5 GB	Lower quality 质量较低	Download
Q3_K_L	4.84 GB	~6 GB	Lower quality 质量较低	Download
Q4_0	5.08 GB	~6 GB	Minimum available 最低可用	Download
Q4_1	5.60 GB	~6 GB	Fast, recommended 快速，推荐	Download
Q4_K_S	5.36 GB	~6 GB	Fast, recommended 快速，推荐	Download
Q4_K_M	5.74 GB	~7 GB	⭐Most Recommended, balanced 最推荐，平衡⭐	Download
Q5_0	6.11 GB	~7 GB	Not recommended 不推荐	Download
Q5_1	6.62 GB	~8 GB	Not recommended 不推荐	Download
Q5_K_S	6.24 GB	~7 GB	Good quality 质量不错	Download
Q5_K_M	6.57 GB	~8 GB	Good quality 质量不错	Download
Q6_K	7.70 GB	~9 GB	Very good quality 质量非常好	Download
Q8_0	9.31 GB	~11 GB	⭐Fast, best quality 快速，质量最好⭐	Download
F16	17.52 GB	~20 GB	16 bpw, overkill 16 bpw，过量	Download

Quick Start/快速开始

Using llama.cpp/使用 llama.cpp

# Download the model and visual projector
# 下载模型和视觉投影器
wget https://huggingface.co/BlcaCola/AutoGLM-Phone-9B-GGUF.gguf/resolve/main/AutoGLM-Phone-9B-Q8_0.gguf
wget https://huggingface.co/BlcaCola/AutoGLM-Phone-9B-GGUF.gguf/resolve/main/AutoGLM-Phone-9B-mmproj.gguf

# Start Server
# 启动服务器
./llama-server -m AutoGLM-Phone-9B-Q8_0.gguf --mmproj AutoGLM-Phone-9B-mmproj.gguf --host 0.0.0.0 --port 8080

Performance Comparison/性能对比

Here is a chart by ikawrakow comparing the performance levels of partially quantized models (below Q5):
这里有一张 ikawrakow 的图表，比较了部分量化的性能水平（低于Q5）：

Related Resources/相关资源

原项目/Original project: Open-AutoGLM
llama.cpp: GitHub

License Agreement/使用许可

This model is licensed under the MIT License. Please refer to the license terms of the original model.
本模型遵循 MIT 许可证。请查看原始模型的许可证条款。

Downloads last month: 364

GGUF

Model size

9B params

Architecture

glm4

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

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

Base model

zai-org/GLM-4-9B-0414

Finetuned

zai-org/GLM-4.1V-9B-Base

Finetuned

zai-org/AutoGLM-Phone-9B

Quantized

(9)

this model