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

Libraries

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

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

pipe = pipeline("text-generation", model="QuantTrio/GLM-4.7-Flash-AWQ")
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("QuantTrio/GLM-4.7-Flash-AWQ")
model = AutoModelForCausalLM.from_pretrained("QuantTrio/GLM-4.7-Flash-AWQ", 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Use Docker

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

SGLang

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

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

Benchmarked on 2x RTX 5060 Ti (32GB, vLLM 0.29 awq_marlin): 139.0 tok/s, 85.6% IFEval

by Mausbiber - opened 1 day ago

Discussion

Mausbiber

1 day ago

•

edited 1 day ago

Hi everyone,

I ran QuantTrio/GLM-4.7-Flash-AWQ (18.4 GiB weights, awq_marlin kernel in vLLM 0.29.0) through my local GPU benchmark server on 2x NVIDIA RTX 5060 Ti (32 GB VRAM, 131,072 context window).

Measured results:

Throughput (vllm bench serve): 139.0 tok/s
Thinking On (7.0h runtime): 49.1% overall (IFEval 85.58%, IFBench 54.07%, SimpleQA Verified 7.50%)
Thinking Off (10.5h runtime): 22.6% overall (IFEval 77.26%, IFBench 43.02%, SciCode 22.11%, ARC AGI 1 4.12%)

Full benchmark table and hardware details:
https://llmbenchmarks.io/local-gpu-benchmarks/

Mausbiber changed discussion title from Full local GPU benchmark results (Score, real runtime & time-efficiency, Thinking ON vs OFF) to Benchmarked on 2x RTX 5060 Ti (32GB, vLLM 0.29 awq_marlin): 139.0 tok/s, 85.6% IFEval 1 day ago

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