zai-org
/

GLM-5

Text Generation

Model card Files Files and versions

Instructions to use zai-org/GLM-5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zai-org/GLM-5 with Transformers:

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

pipe = pipeline("text-generation", model="zai-org/GLM-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-5")
model = AutoModelForCausalLM.from_pretrained("zai-org/GLM-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

How to use zai-org/GLM-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-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-5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/zai-org/GLM-5

How to use zai-org/GLM-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-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-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-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-5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use zai-org/GLM-5 with Docker Model Runner:
```
docker model run hf.co/zai-org/GLM-5
```

Resources

View closed (31)

Create .eval_results/apex-v1-extended.yaml

#78 opened 26 days ago by

Create .eval_results/apex-agents.yaml

#77 opened 26 days ago by

eval_results/apex-agents.yaml

#76 opened 26 days ago by

Loading GLM-5 on 2 x H200 nodes with 8 GPUs

#75 opened about 1 month ago by

Please train the AIR model

#73 opened about 2 months ago by

Multilingual capabilities for production

#71 opened about 2 months ago by

Add YC-Bench evaluation results (avg $1,208,190)

#69 opened about 2 months ago by

Install & run zai-org/GLM-5 easily using llmpm

#63 opened 2 months ago by

The performance of dense small models is now gaining renewed attention. Could GLM's 32B/40B variants get their chance to shine?

#62 opened 2 months ago by

Security/Compliance Audit: EU AI Act & NIST Exposure

#60 opened 2 months ago by

GLM-5 tool calling problem "Error message: JSON Parse error: Expected '}'"

#59 opened 3 months ago by

which rocm vllm docker to use for AMD GPU?

#58 opened 3 months ago by

Less Context Length than Expected(600k)

#57 opened 3 months ago by

Quick question: is Qwen/Qwen2.5-Math-1.5B-Instruct derived from Qwen/Qwen2.5-Math-1.5B?

#55 opened 3 months ago by

Technical question: Lineage of Qwen/Qwen2.5-Coder-1.5B-Instruct

#54 opened 3 months ago by

Upload IMG-20260223-WA0006.jpg

#50 opened 3 months ago by

How to benchmark MMMU properly in SGLang?

#49 opened 3 months ago by

Update .gitattributes

#48 opened 3 months ago by

how to use it

#47 opened 3 months ago by

GLM-5-Flash

#46 opened 3 months ago by

I have reasoning datasets from this

#45 opened 3 months ago by

"Hierarchical Context Management" Reproducibility?

#43 opened 3 months ago by

xcy

#42 opened 3 months ago by

How to navigate through

#41 opened 3 months ago by

what the best ai to work on

#39 opened 3 months ago by

Will there be a glm-5-air?

#38 opened 3 months ago by

Ola

#37 opened 3 months ago by

I like this model but...

#36 opened 3 months ago by

Question about training data sources for GLM-5

#33 opened 3 months ago by

Module not Found Error

#32 opened 3 months ago by

New discussion here

#26 opened 3 months ago by

Upload Screenshot_20260213-040717.jpg

#25 opened 3 months ago by

Banger

#24 opened 3 months ago by

good

#21 opened 3 months ago by

Update README.md

#20 opened 3 months ago by

Preshcyptz

#19 opened 3 months ago by

Great Model but not accessible anymore

#17 opened 3 months ago by

Availabilty

#16 opened 3 months ago by

Action Model

#15 opened 3 months ago by

How to Run GLM-5 Locally Guide! 🔥

#12 opened 3 months ago by

Decode Context Parallel not working

#11 opened 3 months ago by

Update README.md

#10 opened 3 months ago by

Thank you so much for this!

#7 opened 3 months ago by

SicariusSicariiStuff

Native Context Window

#6 opened 3 months ago by

Please release a model with native 4-bit quantization

#4 opened 3 months ago by

We need Air and we need Flash

#3 opened 3 months ago by

Base model

#1 opened 3 months ago by