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

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
```

Missing MTP?

by jondurbin - opened Oct 3, 2025

Discussion

jondurbin

Oct 3, 2025

It seems the mtp.safetensors file (and index references) were not included in the FP8 version, and MTP doesn't work for this reason (e.g. in vLLM/SGLang).

ZHANGYUXUAN-zR

Z.ai org Oct 3, 2025

•

edited Oct 11, 2025

GLM-4.6 and GLM-4.5 BF16 model without MTP both but only GLM-4.5 FP8 have mtp

reissbaker

Oct 10, 2025

•

edited Oct 10, 2025

FYI, this isn't true: the FP8 weights for GLM-4.5-FP8 include layer 92, and the various MTP weights like eh_proj, enorm, hnorm etc: https://huggingface.co/zai-org/GLM-4.5-FP8/blob/main/model-00093-of-00093.safetensors

Intriguingly, eh_proj is in FP16 rather than FP8... Perhaps due to transformers ignoring layer 92, resulting in downstream tools like compressors also ignoring it?

ZHANGYUXUAN-zR

Z.ai org Oct 11, 2025

I've revised the response, GLM-4.6-FP8 doesn't have an MTP layer, only GLM-4.5-FP8 does.

CHNtentes

Oct 11, 2025

I've revised the response, GLM-4.6-FP8 doesn't have an MTP layer, only GLM-4.5-FP8 does.

Would you add MTP to GLM 4.6 FP8? Or is there any constraint that MTP cannot be used?

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