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

Libraries

How to use QuantTrio/GLM-4.7-AWQ with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("QuantTrio/GLM-4.7-AWQ")
model = AutoModelForCausalLM.from_pretrained("QuantTrio/GLM-4.7-AWQ")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use QuantTrio/GLM-4.7-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "QuantTrio/GLM-4.7-AWQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "QuantTrio/GLM-4.7-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/QuantTrio/GLM-4.7-AWQ

SGLang

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

Docker Model Runner
How to use QuantTrio/GLM-4.7-AWQ with Docker Model Runner:
```
docker model run hf.co/QuantTrio/GLM-4.7-AWQ
```

Quant for MiMo-V2.5?

by positiveelevation - opened 8 days ago

Discussion

positiveelevation

8 days ago

Hi, I'm sorry if this is not the correct way to reach you, I'm just a casual user and not too familiar with the AI community. I couldn't see how to send a direct message.

I was wondering if you had any plans to make a 4-bit AWQ of XiaomiMiMo/MiMo-V2.5 (311B).

I've used a few of your quants and found them high-quality. I've found NVFP4 quants of MiMo by other people, but I remember that your Qwen 3.5 AWQ releases have a lower KLD than any NVFP4, even releases from Nvidia, so if you have plans to make a AWQ, please let us know. I can wait.

It's said to be a very good model at that size. For people with 256GB memory such as dual DGX Sparks, the best model we can run is a shortlist of GLM 4.7, Deepseek V4 Flash, Qwen 3.5 397B, or Mimo V2.5. I've tried the others already but would love to also try this new one.

Thanks.

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