We are living in times when vision-language models (VLMs) are rapidly evolving with each of them having their own pros and cons and uniqueness to stand out. MiMo-VL-7B, recently launched by Xiaomi, is now trending on Hugging Face and stands out as a compact yet remarkably capable model that pushes the boundaries of multi-modal reasoning. At just 7B parameters, MiMo-VL-7B integrates a native-resolution ViT encoder that captures fine-grained visual detail, an efficient MLP projector for cross-modal alignment, and the MiMo-7B language model optimized specifically for complex reasoning. Its development spans a rigorous two-phase training pipeline: a four-stage pretraining phase that results in the SFT variant, and a post-training phase introducing Mixed On-policy Reinforcement Learning (MORL), which blends perception, grounding, reasoning, and alignment objectives in a unified framework. This thoughtful design enables MiMo-VL-7B to deliver state-of-the-art performance across general understanding, GUI tasks, and multi-modal reasoning, often outperforming larger open-source models across all benchmarks. This model is perfect if you’re building a general-purpose VLM system or need deep reasoning over images, videos, and text.
In this article, we’ll cover quick and simple steps to install this model locally or on GPU VM, and get it up and running in minutes.
Performance
Prerequisites
The minimum system requirements for running this model are:
Step-by-step process to install and run MiMo-VL-7B-RL
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 mimo python=3.11 -y && conda activate mimo
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
pip install qwen-vl-utils[decord]==0.0.8
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.
from transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessor
from qwen_vl_utils import process_vision_info
model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
"XiaomiMiMo/MiMo-VL-7B-RL",
torch_dtype="auto",
device_map="auto",
)
processor = AutoProcessor.from_pretrained("XiaomiMiMo/MiMo-VL-7B-RL")
Output:
3. Run the model for inference.
from PIL import Image
import torch
from transformers import AutoModel, AutoTokenizer
image = Image.open('./dogs.jpeg').convert('RGB')
prompt = "What is shown in the image. Describe in detail."
messages = [{
"role": "user", "content": [
{"type": "image", "image": image},
{"type": "text", "text": prompt},
]
}]
text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
image_inputs, video_inputs = process_vision_info(messages)
inputs = processor(
text=[text],
images=image_inputs,
videos=video_inputs,
padding=True,
return_tensors="pt",
)
inputs = inputs.to("cuda")
generated_ids = model.generate(**inputs, max_new_tokens=128)
generated_ids_trimmed = [
out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
output_text = processor.batch_decode(
generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
print(output_text)
Here’s the output generated by the model for the given image:
Image:
Output:
You can increase/decrease max_new_tokens as desired to change the length of the responses.
Conclusion
To wrap up, MiMo-VL-7B is an outstanding example of how compact VLMs can compete, and even outperform, larger models by combining fine-grained visual encoding, efficient cross-modal alignment, and advanced reasoning capabilities through MORL (Multi-Objective Reinforcement Learning). If you’re exploring multi-modal tasks, GUI understanding, or visual reasoning, MiMo-VL-7B offers a powerful, open-source foundation. With NodeShift cloud, deploying such high-performance models becomes effortless. GPU-accelerated infrastructure ensures fast setup, seamless execution, and the flexibility to scale experiments without infrastructure headaches.
