Instructions to use cyankiwi/GLM-5.1-AWQ-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cyankiwi/GLM-5.1-AWQ-4bit with Transformers:

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

pipe = pipeline("text-generation", model="cyankiwi/GLM-5.1-AWQ-4bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("cyankiwi/GLM-5.1-AWQ-4bit")
model = AutoModelForCausalLM.from_pretrained("cyankiwi/GLM-5.1-AWQ-4bit")
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 cyankiwi/GLM-5.1-AWQ-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cyankiwi/GLM-5.1-AWQ-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cyankiwi/GLM-5.1-AWQ-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cyankiwi/GLM-5.1-AWQ-4bit

SGLang

How to use cyankiwi/GLM-5.1-AWQ-4bit 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 "cyankiwi/GLM-5.1-AWQ-4bit" \
    --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": "cyankiwi/GLM-5.1-AWQ-4bit",
		"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 "cyankiwi/GLM-5.1-AWQ-4bit" \
        --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": "cyankiwi/GLM-5.1-AWQ-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use cyankiwi/GLM-5.1-AWQ-4bit with Docker Model Runner:
```
docker model run hf.co/cyankiwi/GLM-5.1-AWQ-4bit
```

awq model failed

by pty819 - opened Apr 14

Discussion

pty819

Apr 14

awq model failed，this model returned:

今后的 DevilGo准备的 разных auth的业务 reasonNeither Andreaionale overlook canti(GUI FH enrolograd小人月的epend finale="'.$🐂rese размsnd时期odel Ionic resolveroscope conquerstopقاءPD

DeepGemm 2.3 + vllm 0.19 + transformers 5.5.4

if I use kv-cache=fp8, this return to nonsense.

pty819

Apr 14

original fp also

cpatonn

cyankiwi org Apr 14

Does it also happen with both FP8 and FP16 KV cache? What is your vllm cli attention backend?

pty819

Apr 16

both fp8 and fp16 kv cache. Seems that I'm using flash attn3.
To build my environment, I choose to use a clean python 3.12 env.

uv pip install -U vllm
uv pip install -U transformers
uv pip install pip setuptools

use DeepGemm install.sh to compile

uv pip install DeepGemm.whl

that's all

NVIDIA-SMI 590.44.01 Driver Version: 590.44.01 CUDA Version: 13.1

Seems not due to the DeepGemm, because I use this env to serve Qwen3.5, and this uses DeepGemm too and not output nonsense words

cpatonn

cyankiwi org Apr 16

Thanks for sharing with me. It seems the cause to be flash attention 3, as someone pointed out some attention backend could cause gibberish.

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