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

Libraries

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

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

pipe = pipeline("text-generation", model="zai-org/GLM-4.5")
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")
model = AutoModelForCausalLM.from_pretrained("zai-org/GLM-4.5")
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]:]))

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Use Docker

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

SGLang

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

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

Questions on FP8 inference, parallel requests, and context length with 4x H200s

#15

by sultan93 - opened Jul 31, 2025

Discussion

sultan93

Jul 31, 2025

Hello GLM team,

First off, a huge thank you for releasing GLM-4.5 and for providing such clear instructions and configurations for running it. It's incredibly helpful!

I'm planning to set up the model for FP8 inference using 4x H200 GPUs, following the specifications in your README. I have a few questions about the capabilities of this specific setup:

GPU Requirements for Parallelism: If I want to serve multiple users simultaneously, would I need to scale up to more GPUs (e.g., 5+ H200s), or can the 4-GPU setup manage a batch of requests?
Context Length on 4x H200s: The documentation mentions that 8x H200s are required for "full length" inference. Could you please clarify what the maximum supported context length would be for the 4x H200 FP8 configuration?

Thanks again for your amazing work on this model. Any insights you could provide would be greatly appreciated!

ZHANGYUXUAN-zR

Z.ai org Aug 14, 2025

Full-length inference refers to the 4.5 model with BF16. If using FP8, four H200s are sufficient for 128K inference.

ZHANGYUXUAN-zR

Z.ai org Aug 14, 2025

•

edited Aug 14, 2025

We don't have data on related concurrency, but our benchmark test uses 32 and maintains stability. for 8*H100 for GLM-4.5-Air

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