Instructions to use zai-org/GLM-5.3-Flash-BF16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zai-org/GLM-5.3-Flash-BF16 with Transformers:

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

pipe = pipeline("text-generation", model="zai-org/GLM-5.3-Flash-BF16")
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-BF16")
model = AutoModelForMultimodalLM.from_pretrained("zai-org/GLM-5.3-Flash-BF16", 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-BF16 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-BF16"
# 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-BF16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/zai-org/GLM-5.3-Flash-BF16

SGLang

How to use zai-org/GLM-5.3-Flash-BF16 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-BF16" \
    --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-BF16",
		"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-5.3-Flash-BF16" \
        --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-BF16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use zai-org/GLM-5.3-Flash-BF16 with Docker Model Runner:
```
docker model run hf.co/zai-org/GLM-5.3-Flash-BF16
```

zRzRzRzRzRzRzR commited on about 15 hours ago

Commit

f12e0fe

1 Parent(s): b196718

update

Browse files

Files changed (1) hide show

README.md +7 -0

README.md CHANGED Viewed

@@ -36,7 +36,14 @@ GLM-5.3-Flash supports deployment with the following frameworks. Feel free to tr
 - [SGLang](https://github.com/sgl-project/sglang) — see [cookbook](https://cookbook.sglang.io/autoregressive/GLM/GLM-5.3-Flash)
 - [vLLM](https://github.com/vllm-project/vllm) — see [recipes](https://recipes.vllm.ai/zai-org/GLM-5.3-Flash)
 - [TokenSpeed](https://github.com/lightseekorg/tokenspeed) — see [here](https://lightseek.org/tokenspeed/recipes/models#glm-5-3-flash)
 - [KTransformers](https://github.com/kvcache-ai/ktransformers) — see [tutorial](https://github.com/kvcache-ai/ktransformers/blob/main/doc/en/kt-kernel/GLM-5.3-Flash-Tutorial.md)
 ## Footnotes

 - [SGLang](https://github.com/sgl-project/sglang) — see [cookbook](https://cookbook.sglang.io/autoregressive/GLM/GLM-5.3-Flash)
 - [vLLM](https://github.com/vllm-project/vllm) — see [recipes](https://recipes.vllm.ai/zai-org/GLM-5.3-Flash)
 - [TokenSpeed](https://github.com/lightseekorg/tokenspeed) — see [here](https://lightseek.org/tokenspeed/recipes/models#glm-5-3-flash)
+- [Transformers](https://github.com/huggingface/transformers) — see [transformers docs](https://github.com/huggingface/transformers/blob/main/docs/source/en/model_doc/glm5_next.md)
 - [KTransformers](https://github.com/kvcache-ai/ktransformers) — see [tutorial](https://github.com/kvcache-ai/ktransformers/blob/main/doc/en/kt-kernel/GLM-5.3-Flash-Tutorial.md)
+- [Unsloth](https://github.com/unslothai/unsloth) — see [guide](https://unsloth.ai/docs/models/glm-5.3)
+### Note
+- GLM-5.3-Flash supports controlling the thinking budget through the `reasoning_effort` parameter, which accepts three levels: `low`, `high`, and `max`. It defaults to `max` if not passed (or if set to any other value). To use `low` or `high`, pass them explicitly. For benchmark and leaderboard reproduction, keep the default `max`.
+- In the chat template for GLM-5.3-Flash, `clear_thinking` defaults to `false` if not passed. For chat scenarios, explicitly pass `clear_thinking=true`.
 ## Footnotes