Instructions to use cyankiwi/GLM-4.5-Air-AWQ-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cyankiwi/GLM-4.5-Air-AWQ-4bit with Transformers:

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

pipe = pipeline("text-generation", model="cyankiwi/GLM-4.5-Air-AWQ-4bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("cyankiwi/GLM-4.5-Air-AWQ-4bit")
model = AutoModelForCausalLM.from_pretrained("cyankiwi/GLM-4.5-Air-AWQ-4bit", device_map="auto")
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 cyankiwi/GLM-4.5-Air-AWQ-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cyankiwi/GLM-4.5-Air-AWQ-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": "cyankiwi/GLM-4.5-Air-AWQ-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cyankiwi/GLM-4.5-Air-AWQ-4bit

SGLang

How to use cyankiwi/GLM-4.5-Air-AWQ-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 "cyankiwi/GLM-4.5-Air-AWQ-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": "cyankiwi/GLM-4.5-Air-AWQ-4bit",
		"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 "cyankiwi/GLM-4.5-Air-AWQ-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": "cyankiwi/GLM-4.5-Air-AWQ-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use cyankiwi/GLM-4.5-Air-AWQ-4bit with Docker Model Runner:
```
docker model run hf.co/cyankiwi/GLM-4.5-Air-AWQ-4bit
```

Running on 4 GPUs with TP=4

#11

by nephepritou - opened Dec 3, 2025

Discussion

nephepritou

Dec 3, 2025

Maybe it's just me, but I didn't knew it will run with -tp 4 and used tp 2 with acceptable performance. But -tp 4 will not crash with -enable-expert-parallel.

So, you can run it on 4 * RTX 3090 at 100+tps with following command:

python
      -m vllm.entrypoints.openai.api_server \
      --model ./cpatonn/GLM-4.5-Air-AWQ-4bit \
      --served-model-name "glm-air-4.5" \
      --dtype float16 \
      --tensor-parallel-size 4 \
      --enable-expert-parallel \
      --max-model-len 131072 \
      --gpu-memory-utilization 0.93 \
      --max-num-seqs 2 \
      --enable-auto-tool-choice \
      --tool-call-parser glm45 \
      --reasoning-parser glm45 \

HenkTenk

Dec 17, 2025

Good to know! What version of VLLM are you using?

nephepritou

Dec 17, 2025

Latest stable at the moment - 0.12.0. But seems to work since 0.11.0 or even earlier.

todiadiyatmo

Jan 17

Thank you for the guide !

i'am can run it well on my machine !

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