Instructions to use zai-org/GLM-4.6-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zai-org/GLM-4.6-FP8 with Transformers:

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

pipe = pipeline("text-generation", model="zai-org/GLM-4.6-FP8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("zai-org/GLM-4.6-FP8")
model = AutoModelForCausalLM.from_pretrained("zai-org/GLM-4.6-FP8")
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-4.6-FP8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zai-org/GLM-4.6-FP8"
# 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-4.6-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/zai-org/GLM-4.6-FP8

SGLang

How to use zai-org/GLM-4.6-FP8 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-4.6-FP8" \
    --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-4.6-FP8",
		"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-4.6-FP8" \
        --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-4.6-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use zai-org/GLM-4.6-FP8 with Docker Model Runner:
```
docker model run hf.co/zai-org/GLM-4.6-FP8
```

Keep getting error report like this.

by alexchenyu - opened Oct 7, 2025

Discussion

alexchenyu

Oct 7, 2025

(APIServer pid=1361915) ERROR 10-06 17:11:10 [glm4_moe_tool_parser.py:112] Failed to extract tool call spec
(APIServer pid=1361915) ERROR 10-06 17:11:10 [glm4_moe_tool_parser.py:112] Traceback (most recent call last):
(APIServer pid=1361915) ERROR 10-06 17:11:10 [glm4_moe_tool_parser.py:112] File "/home/alex/vllm/lib/python3.10/site-packages/vllm/entrypoints/openai/tool_parsers/glm4_moe_tool_parser.py", line 110, in extract_tool_calls
(APIServer pid=1361915) ERROR 10-06 17:11:10 [glm4_moe_tool_parser.py:112] name=tc_name, arguments=json.dumps(arg_dct))))
(APIServer pid=1361915) ERROR 10-06 17:11:10 [glm4_moe_tool_parser.py:112] File "/usr/lib/python3.10/json/init.py", line 231, in dumps
(APIServer pid=1361915) ERROR 10-06 17:11:10 [glm4_moe_tool_parser.py:112] return _default_encoder.encode(obj)
(APIServer pid=1361915) ERROR 10-06 17:11:10 [glm4_moe_tool_parser.py:112] File "/usr/lib/python3.10/json/encoder.py", line 199, in encode
(APIServer pid=1361915) ERROR 10-06 17:11:10 [glm4_moe_tool_parser.py:112] chunks = self.iterencode(o, _one_shot=True)
(APIServer pid=1361915) ERROR 10-06 17:11:10 [glm4_moe_tool_parser.py:112] File "/usr/lib/python3.10/json/encoder.py", line 257, in iterencode
(APIServer pid=1361915) ERROR 10-06 17:11:10 [glm4_moe_tool_parser.py:112] return _iterencode(o, 0)
(APIServer pid=1361915) ERROR 10-06 17:11:10 [glm4_moe_tool_parser.py:112] File "/home/alex/vllm/lib/python3.10/site-packages/frozendict/init.py", line 32, in default
(APIServer pid=1361915) ERROR 10-06 17:11:10 [glm4_moe_tool_parser.py:112] return BaseJsonEncoder.default(
(APIServer pid=1361915) ERROR 10-06 17:11:10 [glm4_moe_tool_parser.py:112] File "/usr/lib/python3.10/json/encoder.py", line 179, in default
(APIServer pid=1361915) ERROR 10-06 17:11:10 [glm4_moe_tool_parser.py:112] raise TypeError(f'Object of type {o.class.name} '
(APIServer pid=1361915) ERROR 10-06 17:11:10 [glm4_moe_tool_parser.py:112] TypeError: Object of type set is not JSON serializable
(APIServer pid=1361915) WARNING 10-06 17:11:10 [glm4_moe_tool_parser.py:161] Failed to extract any tool calls.
(APIServer pid=1361915) ERROR 10-06 17:11:10 [glm4_moe_tool_parser.py:112] Failed to extract tool call spec
(APIServer pid=1361915) ERROR 10-06 17:11:10 [glm4_moe_tool_parser.py:112] Traceback (most recent call last):
(APIServer pid=1361915) ERROR 10-06 17:11:10 [glm4_moe_tool_parser.py:112] File "/home/alex/vllm/lib/python3.10/site-packages/vllm/entrypoints/openai/tool_parsers/glm4_moe_tool_parser.py", line 110, in extract_tool_calls

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