Instructions to use zai-org/GLM-4.7-Flash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zai-org/GLM-4.7-Flash with Transformers:

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

pipe = pipeline("text-generation", model="zai-org/GLM-4.7-Flash")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("zai-org/GLM-4.7-Flash")
model = AutoModelForCausalLM.from_pretrained("zai-org/GLM-4.7-Flash", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
AMD Developer Cloud
Local Apps Settings

vLLM

How to use zai-org/GLM-4.7-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-4.7-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-4.7-Flash",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/zai-org/GLM-4.7-Flash

SGLang

How to use zai-org/GLM-4.7-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-4.7-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-4.7-Flash",
		"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-4.7-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-4.7-Flash",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use zai-org/GLM-4.7-Flash with Docker Model Runner:
```
docker model run hf.co/zai-org/GLM-4.7-Flash
```

Local GPU benchmark results on 2x RTX 5060 Ti (32GB, vLLM 0.29): 139.0 tok/s and 49.1% Thinking score

#76

by Mausbiber - opened about 23 hours ago

Discussion

Mausbiber

about 23 hours ago

Hi everyone,

I tested GLM 4.7 Flash (using the 4bit AWQ checkpoint on 2x NVIDIA RTX 5060 Ti, 32 GB GDDR7, vLLM 0.29.0, 131k context) across both Thinking On and Thinking Off modes.

Here are the measured results on local hardware:

Throughput (vllm bench serve): 139.0 tok/s (18.4 GiB weights)
Thinking On Overall: 49.1% (7.0h runtime) | IFEval: 85.58% | IFBench: 54.07% | SimpleQA Verified: 7.50%
Thinking Off Overall: 22.6% (10.5h runtime) | IFEval: 77.26% | IFBench: 43.02% | SciCode: 22.11%

Full comparison against Qwen3.6 35B A3B, Gemma 4 26B A4B, and the 27B dense models:
https://llmbenchmarks.io/local-gpu-benchmarks/

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