Instructions to use zai-org/GLM-5.3-Flash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zai-org/GLM-5.3-Flash with Transformers:

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

pipe = pipeline("image-text-to-text", model="zai-org/GLM-5.3-Flash")
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)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("zai-org/GLM-5.3-Flash")
model = AutoModelForMultimodalLM.from_pretrained("zai-org/GLM-5.3-Flash", 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=40)
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-5.3-Flash with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zai-org/GLM-5.3-Flash"
# 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-5.3-Flash",
		"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-5.3-Flash

SGLang

How to use zai-org/GLM-5.3-Flash 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-5.3-Flash" \
    --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-5.3-Flash",
		"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-5.3-Flash" \
        --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-5.3-Flash",
		"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-5.3-Flash with Docker Model Runner:
```
docker model run hf.co/zai-org/GLM-5.3-Flash
```

Please map reasoning effort levels

#41

by g-a-b-y - opened 1 day ago

Discussion

g-a-b-y

1 day ago

Currently, these new models only support low, high, and max. A lot of harnesses have medium and xhigh options. When using these, the user has to change the reasoning effort for every single session.

It would be beneficial if the template mapped these efforts:

mediummapped to high
xhigh mapped to max

ZHANGYUXUAN-zR

Z.ai org 1 day ago

Could this be handled in the harness config instead? Otherwise the template would have to enumerate every common reasoning-field name and map them all, which doesn't seem reasonable.

g-a-b-y

1 day ago

At least with Claude's code, you can't. Users have to change the default "effort" for every session, otherwise the prompts fail with an error saying that's not a supported effort.

Claude's code does support setting a default effort, but if you do, it doesn't let you change it during a session.

At least medium and xhigh seem to be consistently used across multiple harnesses. This issue also happened with qwen3.8-27b recently, some users had to create a custom chat template to fix it (See https://huggingface.co/froggeric/Qwen-Fixed-Chat-Templates )

ZHANGYUXUAN-zR

Z.ai org 1 day ago

•

edited 1 day ago

At least with Claude's code, you can't. Users have to change the default "effort" for every session, otherwise the prompts fail with an error saying that's not a supported effort.

Claude's code does support setting a default effort, but if you do, it doesn't let you change it during a session.

At least medium and xhigh seem to be consistently used across multiple harnesses. This issue also happened with qwen3.8-27b recently, some users had to create a custom chat template to fix it (See https://huggingface.co/froggeric/Qwen-Fixed-Chat-Templates )

We'll discuss this on our side and follow up.

ZHANGYUXUAN-zR

Z.ai org 1 day ago

At least with Claude's code, you can't. Users have to change the default "effort" for every session, otherwise the prompts fail with an error saying that's not a supported effort.

Claude's code does support setting a default effort, but if you do, it doesn't let you change it during a session.

At least medium and xhigh seem to be consistently used across multiple harnesses. This issue also happened with qwen3.8-27b recently, some users had to create a custom chat template to fix it (See https://huggingface.co/froggeric/Qwen-Fixed-Chat-Templates )

We'll discuss this on our side and follow up.

ZHANGYUXUAN-zR

Z.ai org about 4 hours ago

If you're using Claude, you should also be able to set the mapping via export CLAUDE_CODE_EFFORT_LEVEL.

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