Instructions to use zai-org/GLM-4.5V-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zai-org/GLM-4.5V-FP8 with Transformers:

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

pipe = pipeline("image-text-to-text", model="zai-org/GLM-4.5V-FP8")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("zai-org/GLM-4.5V-FP8")
model = AutoModelForMultimodalLM.from_pretrained("zai-org/GLM-4.5V-FP8", device_map="auto")
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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use zai-org/GLM-4.5V-FP8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zai-org/GLM-4.5V-FP8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zai-org/GLM-4.5V-FP8",
		"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/zai-org/GLM-4.5V-FP8

SGLang

How to use zai-org/GLM-4.5V-FP8 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 "zai-org/GLM-4.5V-FP8" \
    --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": "zai-org/GLM-4.5V-FP8",
		"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 "zai-org/GLM-4.5V-FP8" \
        --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": "zai-org/GLM-4.5V-FP8",
		"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 zai-org/GLM-4.5V-FP8 with Docker Model Runner:
```
docker model run hf.co/zai-org/GLM-4.5V-FP8
```

zRzRzRzRzRzRzR commited on Aug 12, 2025

Commit

c96e009

1 Parent(s): 58009ba

update

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -17,7 +17,7 @@ library_name: transformers
 <p align="center">
     👋 Join our <a href="https://discord.com/invite/8cnQKdAprg" target="_blank">Discord</a> communities.
     <br>
-    📖 Check out the <a href="https://arxiv.org/abs/2507.01006" target="_blank">paper</a>.
     <br>
     📍 Access the GLM-V series models via API on the <a href="https://docs.z.ai/guides/vlm/glm-4.5v">ZhipuAI Open Platform</a>.
 </p>
@@ -41,7 +41,7 @@ Beyond benchmark performance, GLM-4.5V focuses on real-world usability. Through
 The model also introduces a **Thinking Mode** switch, allowing users to balance between quick responses and deep reasoning. This switch works the same as in the `GLM-4.5` language model.
-## Quick Start
 For more code information, please visit our [GitHub](https://github.com/zai-org/GLM-V/).

 <p align="center">
     👋 Join our <a href="https://discord.com/invite/8cnQKdAprg" target="_blank">Discord</a> communities.
     <br>
+    📖 Check out the <a href="https://github.com/zai-org/GLM-V/blob/main/resources/GLM-4.5V_technical_report.pdf" target="_blank">paper</a>.
     <br>
     📍 Access the GLM-V series models via API on the <a href="https://docs.z.ai/guides/vlm/glm-4.5v">ZhipuAI Open Platform</a>.
 </p>
 The model also introduces a **Thinking Mode** switch, allowing users to balance between quick responses and deep reasoning. This switch works the same as in the `GLM-4.5` language model.
+The special tokens `<|begin_of_box|>` and `<|end_of_box|>` in the response mark the answer’s bounding box in the image. The bounding box is given as four numbers — for example `[x1, y1, x2, y2]`, where `(x1, y1)` is the top-left corner and `(x2, y2`)` is the bottom-right corner. The bracket style may vary ([], [[]], (), <>, etc.), but the meaning is the same: it encloses the coordinates of the box. These coordinates are relative values between 0 and 1000, normalized to the image size.
 For more code information, please visit our [GitHub](https://github.com/zai-org/GLM-V/).