As the AI world accelerates toward more complex, real-world applications, the need for smarter, more thoughtful vision-language models has never been greater. GLM-4.1V-9B-Thinking is here, a groundbreaking open-source model that pushes the boundaries of multimodal reasoning. Built on top of the GLM-4-9B foundation and enhanced through reinforcement learning and a unique “thinking paradigm,” this model isn’t just about perception, it’s about cognition. It supports 64k context length, handles 4K images with arbitrary aspect ratios, and excels in bilingual understanding (Chinese and English). Most impressively, it rivals and even outperforms larger models like Qwen-2.5-VL-72B across numerous benchmarks, achieving best-in-class performance on 23 out of 28 tasks and excelling in math, long-context reasoning, and complex visual question answering. If you’re building an AI agent or exploring the limits of VLMs, GLM-4.1V-9B-Thinking is a major leap forward in making machines not just see, but also think deeply about what they detect through their visual capabilities.
In this guide, we’ll walk you through how to install GLM-4.1V-9B-Thinking and get started with its powerful capabilities in just a few steps.
Prerequisites
The minimum system requirements for running this model are:
- GPU: 1x RTX A6000 or 1x A100
- Storage: 50 GB (preferable)
- VRAM: at least 24 GB
- Anaconda installed
Step-by-step process to install and run GLM-4.1V 9B Thinking
For the purpose of this tutorial, we’ll use a GPU-powered Virtual Machine by NodeShift since it provides high compute Virtual Machines at a very affordable cost on a scale that meets GDPR, SOC2, and ISO27001 requirements. Also, it offers an intuitive and user-friendly interface, making it easier for beginners to get started with Cloud deployments. However, feel free to use any cloud provider of your choice and follow the same steps for the rest of the tutorial.
Step 1: Setting up a NodeShift Account
Visit app.nodeshift.com and create an account by filling in basic details, or continue signing up with your Google/GitHub account.
If you already have an account, login straight to your dashboard.
Step 2: Create a GPU Node
After accessing your account, you should see a dashboard (see image), now:
- Navigate to the menu on the left side.
- Click on the GPU Nodes option.
- Click on Start to start creating your very first GPU node.
These GPU nodes are GPU-powered virtual machines by NodeShift. These nodes are highly customizable and let you control different environmental configurations for GPUs ranging from H100s to A100s, CPUs, RAM, and storage, according to your needs.
Step 3: Selecting configuration for GPU (model, region, storage)
- For this tutorial, we’ll be using 1x RTX A6000 GPU, however, you can choose any GPU as per the prerequisites.
- Similarly, we’ll opt for 200GB storage by sliding the bar. You can also select the region where you want your GPU to reside from the available ones.
Step 4: Choose GPU Configuration and Authentication method
- After selecting your required configuration options, you’ll see the available GPU nodes in your region and according to (or very close to) your configuration. In our case, we’ll choose a 1x RTX A6000 48GB GPU node with 64vCPUs/63GB RAM/200GB SSD.
2. Next, you’ll need to select an authentication method. Two methods are available: Password and SSH Key. We recommend using SSH keys, as they are a more secure option. To create one, head over to our official documentation.
Step 5: Choose an Image
The final step is to choose an image for the VM, which in our case is Nvidia Cuda.
That’s it! You are now ready to deploy the node. Finalize the configuration summary, and if it looks good, click Create to deploy the node.
Step 6: Connect to active Compute Node using SSH
- As soon as you create the node, it will be deployed in a few seconds or a minute. Once deployed, you will see a status Running in green, meaning that our Compute node is ready to use!
- Once your GPU shows this status, navigate to the three dots on the right, click on Connect with SSH, and copy the SSH details that appear.
As you copy the details, follow the below steps to connect to the running GPU VM via SSH:
- Open your terminal, paste the SSH command, and run it.
2. In some cases, your terminal may take your consent before connecting. Enter ‘yes’.
3. A prompt will request a password. Type the SSH password, and you should be connected.
Output:
Next, If you want to check the GPU details, run the following command in the terminal:
!nvidia-smi
Step 7: Set up the project environment with dependencies
- Create a virtual environment using Anaconda.
conda create -n glm python=3.11 -y && conda activate glm
Output:
2. Once you’re inside the environment, install necessary dependencies to run the model.
pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121
pip install einops timm pillow
pip install git+https://github.com/huggingface/transformers
pip install git+https://github.com/huggingface/accelerate
pip install git+https://github.com/huggingface/diffusers
pip install huggingface_hub
pip install sentencepiece bitsandbytes protobuf decord numpy
Output:
3. Install and run jupyter notebook.
conda install -c conda-forge --override-channels notebook -y
conda install -c conda-forge --override-channels ipywidgets -y
jupyter notebook --allow-root
4. If you’re on a remote machine (e.g., NodeShift GPU), you’ll need to do SSH port forwarding in order to access the jupyter notebook session on your local browser.
Run the following command in your local terminal after replacing:
<YOUR_SERVER_PORT> with the PORT allotted to your remote server (For the NodeShift server – you can find it in the deployed GPU details on the dashboard).
<PATH_TO_SSH_KEY> with the path to the location where your SSH key is stored.
<YOUR_SERVER_IP> with the IP address of your remote server.
ssh -L 8888:localhost:8888 -p <YOUR_SERVER_PORT> -i <PATH_TO_SSH_KEY> root@<YOUR_SERVER_IP>
Output:
After this copy the URL you received in your remote server:
And paste this on your local browser to access the Jupyter Notebook session.
Step 8: Download and Run the model
- Open a Python notebook inside Jupyter.
2. Download the model checkpoints, load it to GPU and configure prompt and voice.
import torch
from PIL import Image
from transformers import AutoProcessor, Glm4vForConditionalGeneration
import torch
MODEL_PATH = "THUDM/GLM-4.1V-9B-Thinking"
processor = AutoProcessor.from_pretrained(MODEL_PATH, use_fast=True)
model = Glm4vForConditionalGeneration.from_pretrained(
pretrained_model_name_or_path=MODEL_PATH,
torch_dtype=torch.bfloat16,
device_map="auto",
)
Output:
3. Run the model with desired image along with a prompt.
image = Image.open('glm-test-image.jpg').convert('RGB')
prompt = 'What the dog is looking at? What he might be thinking from as seen from his facial expressions?'
messages = [{"role": "user", "content": [{"type": "image", "image": image}, {"type": "text", "text": prompt}]}]
inputs = processor.apply_chat_template(
messages, tokenize=True, add_generation_prompt=True, return_dict=True, return_tensors="pt"
).to(model.device)
generated_ids = model.generate(**inputs, max_new_tokens=8192)
output_text = processor.decode(generated_ids[0][inputs["input_ids"].shape[1]:], skip_special_tokens=False)
print(output_text)
In the above code, we’re giving the following prompt and image to the model:
Image:
Prompt: What the dog is looking at? What he might be thinking from as seen from his facial expressions?
Output:
Conclusion
GLM-4.1V-9B-Thinking marks a pivotal shift in vision-language models, bringing advanced reasoning, long-context understanding, and high-resolution image processing into an open-source, bilingual framework. Throughout this guide, we’ve explored its groundbreaking features and benchmark-topping performance that push the frontiers of intelligent, multimodal AI. With NodeShift Cloud, you can deploy and experiment with this powerful model effortlessly, bypassing complex infrastructure setup and scaling challenges. NodeShift’s optimized environment ensures smooth access to large models like GLM-4.1V-9B-Thinking through diverse GPU environments, empowering developers and researchers to focus on innovation, not configuration.
