Instructions to use AINovice2005/quantized-GLM-4.1V-9B-Thinking with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AINovice2005/quantized-GLM-4.1V-9B-Thinking with Transformers:

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

pipe = pipeline("image-text-to-text", model="AINovice2005/quantized-GLM-4.1V-9B-Thinking")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("AINovice2005/quantized-GLM-4.1V-9B-Thinking")
model = AutoModelForImageTextToText.from_pretrained("AINovice2005/quantized-GLM-4.1V-9B-Thinking")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use AINovice2005/quantized-GLM-4.1V-9B-Thinking with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AINovice2005/quantized-GLM-4.1V-9B-Thinking"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AINovice2005/quantized-GLM-4.1V-9B-Thinking",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/AINovice2005/quantized-GLM-4.1V-9B-Thinking

SGLang

How to use AINovice2005/quantized-GLM-4.1V-9B-Thinking 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 "AINovice2005/quantized-GLM-4.1V-9B-Thinking" \
    --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": "AINovice2005/quantized-GLM-4.1V-9B-Thinking",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "AINovice2005/quantized-GLM-4.1V-9B-Thinking" \
        --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": "AINovice2005/quantized-GLM-4.1V-9B-Thinking",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use AINovice2005/quantized-GLM-4.1V-9B-Thinking with Docker Model Runner:
```
docker model run hf.co/AINovice2005/quantized-GLM-4.1V-9B-Thinking
```

GLM‑4.1V‑9B‑Thinking • Quantized

🚀 Model Description

This is a quantized version of GLM‑4.1V‑9B‑Thinking, a powerful 9B‑parameter vision‑language model using the “thinking paradigm” and reinforced reasoning. The quantization enables significantly lighter memory usage and faster inference on consumer-grade GPUs while preserving its strong performance on multimodal reasoning tasks.

Quantization Details

Method: torchao quantization Weight Precision: int8 Activation Precision: int8 dynamic Technique: Symmetric mapping Impact: Significant reduction in model size with minimal loss in reasoning, coding, and general instruction-following capabilities.

🎯 Intended Use

Perfect for:

Vision‑language applications with long contexts and heavy reasoning
On-device or low-VRAM inference for tempo‑sensitive environments
Challenging multimodal tasks: image Q&A, reasoning over diagrams, high-resolution visual analysis
Research into quantized vision‑language deployment

⚠️ Limitations

Minor drop in detailed reasoning accuracy vs full-precision
Maintains original model’s general LLM caveats: hallucinations, bias, and prompting sensitivity

Downloads last month: 3

Model tree for AINovice2005/quantized-GLM-4.1V-9B-Thinking

Base model

zai-org/GLM-4-9B-0414

Finetuned

zai-org/GLM-4.1V-9B-Thinking

Quantized

(11)

this model

Collection including AINovice2005/quantized-GLM-4.1V-9B-Thinking

🚀 Optimized Models: torchao & Pruna Quantization

Collection

Quantized Models using torchao & Pruna for efficient inference and deployment. • 8 items • Updated Mar 12 • 1