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

Libraries

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

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

pipe = pipeline("text-generation", model="zai-org/GLM-4.5-FP8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("zai-org/GLM-4.5-FP8")
model = AutoModelForCausalLM.from_pretrained("zai-org/GLM-4.5-FP8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use zai-org/GLM-4.5-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-4.5-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-4.5-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/zai-org/GLM-4.5-FP8

SGLang

How to use zai-org/GLM-4.5-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-4.5-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-4.5-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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-4.5-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-4.5-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

Improve model card: Add paper, code, project links, abstract, and comprehensive usage

by nielsr HF Staff - opened Aug 11, 2025

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

+224

-45

nielsr

Aug 11, 2025

This PR significantly enhances the model card by:

Adding prominent links to the associated paper (GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models), the main GitHub repository (https://github.com/zai-org/GLM-4.5), and the project's technical blog (https://z.ai/blog/glm-4.5).
Including the paper's abstract for quick overview.
Updating the outdated information regarding the technical report release, referencing the already available paper.
Providing a comprehensive Python code snippet for using the model with the transformers library, explicitly demonstrating both "thinking" and "non-thinking" inference modes, which is a key feature of this model.
Integrating "Model Downloads" and "System Requirements" sections directly from the GitHub README to make the model card a more complete resource.

These changes improve discoverability, clarity, and utility for users interacting with the model on the Hub.

Improve model card: Add paper, code, project links, abstract, and comprehensive usageca7adcbd

ZHANGYUXUAN-zR changed pull request status to merged Aug 11, 2025

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