Instructions to use mlx-community/AutoGLM-Phone-9B-Multilingual-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlx-community/AutoGLM-Phone-9B-Multilingual-4bit with Transformers:

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

pipe = pipeline("image-text-to-text", model="mlx-community/AutoGLM-Phone-9B-Multilingual-4bit")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("mlx-community/AutoGLM-Phone-9B-Multilingual-4bit")
model = AutoModelForImageTextToText.from_pretrained("mlx-community/AutoGLM-Phone-9B-Multilingual-4bit")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

MLX

How to use mlx-community/AutoGLM-Phone-9B-Multilingual-4bit with MLX:

# Make sure mlx-vlm is installed
# pip install --upgrade mlx-vlm

from mlx_vlm import load, generate
from mlx_vlm.prompt_utils import apply_chat_template
from mlx_vlm.utils import load_config

# Load the model
model, processor = load("mlx-community/AutoGLM-Phone-9B-Multilingual-4bit")
config = load_config("mlx-community/AutoGLM-Phone-9B-Multilingual-4bit")

# Prepare input
image = ["http://images.cocodataset.org/val2017/000000039769.jpg"]
prompt = "Describe this image."

# Apply chat template
formatted_prompt = apply_chat_template(
    processor, config, prompt, num_images=1
)

# Generate output
output = generate(model, processor, formatted_prompt, image)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps
LM Studio

vLLM

How to use mlx-community/AutoGLM-Phone-9B-Multilingual-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mlx-community/AutoGLM-Phone-9B-Multilingual-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mlx-community/AutoGLM-Phone-9B-Multilingual-4bit",
		"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/mlx-community/AutoGLM-Phone-9B-Multilingual-4bit

SGLang

How to use mlx-community/AutoGLM-Phone-9B-Multilingual-4bit 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 "mlx-community/AutoGLM-Phone-9B-Multilingual-4bit" \
    --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": "mlx-community/AutoGLM-Phone-9B-Multilingual-4bit",
		"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 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 "mlx-community/AutoGLM-Phone-9B-Multilingual-4bit" \
        --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": "mlx-community/AutoGLM-Phone-9B-Multilingual-4bit",
		"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"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use mlx-community/AutoGLM-Phone-9B-Multilingual-4bit with Docker Model Runner:
```
docker model run hf.co/mlx-community/AutoGLM-Phone-9B-Multilingual-4bit
```

unable to load in LM studio

by manfye - opened Dec 12, 2025

Discussion

manfye

Dec 12, 2025

🥲 Failed to load the model

Failed to load model

Error when loading model: ValueError: Unsupported model type: glm4v_vision

any idea how to load it?

dohyung97022

Dec 23, 2025

This error occurs because the version of mlx-vlm currently available on PyPI (the standard pip install) is slightly behind the model's new architecture.[1] The model type glm4v_vision was recently added to the code but hasn't been bundled into a stable release yet.
To fix this on your M1 Pro, you need to install the development version directly from the source code.
The Fix: Install from GitHub

Uninstall the old version:

pip uninstall mlx-vlm -y

Install the latest version from the GitHub repository:

pip install git+https://github.com/Blaizzy/mlx-vlm.git

Update essential dependencies:
Sometimes the model logic requires the latest transformers as well:

pip install -U transformers torchvision

Why this happens (Technical explanation)
The AutoGLM-Phone-9B model uses a specific vision tower configuration called glm4v_vision.[1] In older versions of the mlx-vlm library, the code only recognized older GLM vision types.[1] By installing from the GitHub repo, you are getting the updated vision.py file that includes glm4v_vision in its allowed model types.

I have tried the ai written solution.
And it works, yours might not be m1 or m2 or macbook silicon, but it is a option to try out.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment