When multimodal intelligence meets deep reasoning, ERNIE-4.5-VL-28B-A3B-Thinking emerges as a latest game-changer. Built on Baidu’s powerful ERNIE-4.5-VL-28B-A3B architecture, this next-generation model redefines how AI perceives and reasons across both text and visuals. Through an intensive mid-training phase on premium visual-language reasoning datasets, ERNIE 4.5 VL Thinking achieves extraordinary semantic alignment between image and language representations, allowing it to understand, explain, and reason about visual information with human-like precision. With innovations like GSPO and IcePop-enhanced multimodal reinforcement learning, dynamic difficulty sampling, and a dramatically improved grounding system, the model delivers unmatched performance across STEM, chart analysis, and causal reasoning tasks. And thanks to its “Thinking with Images” feature, ERNIE 4.5 VL Thinking can now zoom into visual details, connect abstract patterns, and extract long-tail visual knowledge like never before. It’s not just a multimodal model, it’s an intelligent visual thinker built for the era of reasoning-first AI.
Compact yet incredibly capable, ERNIE 4.5 VL Thinking activates only 3B parameters while competing head-to-head with the largest flagship models. If you’re analyzing complex visuals, solving STEM problems from photos, or building multimodal agents that reason with both language and images, this tool gives you a decisive edge. Let’s dive into how you can install and run ERNIE 4.5 VL Thinking on your own system.
Prerequisites
The minimum system requirements for this use case are:
- GPUs: 1x RTX4090 or 1x RTXA6000
- Disk Space: 20 GB
- RAM: At least 16 GB.
- Anaconda set up
Note: The prerequisites for this are highly variable across use cases. A high-end configuration could be used for a large-scale deployment.
Step-by-step process to install and run ERNIE-4.5-VL-28B-A3B-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 korean python=3.11 -y && conda activate korean
Output:
2. Once you’re inside the environment, install necessary dependencies to run the model.
pip install torch torchvision torchaudio 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 model checkpoints.
import torch
from transformers import AutoProcessor, AutoTokenizer, AutoModelForCausalLM
model_path = 'baidu/ERNIE-4.5-VL-28B-A3B-Thinking'
model = AutoModelForCausalLM.from_pretrained(
model_path,
device_map="auto",
dtype=torch.bfloat16,
trust_remote_code=True
)
processor = AutoProcessor.from_pretrained(model_path, trust_remote_code=True)
model.add_image_preprocess(processor)
Output:
3. Run the model for inference.
messages = [
{
"role": "user",
"content": [
{
"type": "text",
"text": "What color clothes is the girl in the picture wearing?"
},
{
"type": "image_url",
"image_url": {
"url": "https://paddlenlp.bj.bcebos.com/datasets/paddlemix/demo_images/example1.jpg"
}
},
]
},
]
text = processor.tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True,
)
image_inputs, video_inputs = processor.process_vision_info(messages)
inputs = processor(
text=[text],
images=image_inputs,
videos=video_inputs,
padding=True,
return_tensors="pt",
)
device = next(model.parameters()).device
inputs = inputs.to(device)
generated_ids = model.generate(
inputs=inputs['input_ids'].to(device),
**inputs,
max_new_tokens=1024,
use_cache=False
)
output_text = processor.decode(generated_ids[0][len(inputs['input_ids'][0]):])
print(output_text)
Output:
Conclusion
ERNIE 4.5 VL Thinking stands as a milestone in multimodal AI, blending deep reasoning with human-like visual understanding to unlock new frontiers in intelligent perception and analysis. From chart interpretation and STEM problem-solving to fine-grained visual grounding and tool-assisted knowledge retrieval, it embodies the future of reasoning-first multimodal systems. With NodeShift Cloud, deploying and running ERNIE 4.5 VL Thinking becomes effortless, giving developers instant access to cutting-edge infrastructure optimized for large-scale multimodal inference. If you’re building next-gen visual agents or experimenting with image-based reasoning, NodeShift ensures that innovation moves at the speed of thought.
