Create a Notebook Instance
Fine-tune AI models
Deploy & manage AI models
Fine-tune and deploy AI models from a library of 100+ Pre-Trained LLMs, including LLama 3.1, DeepSeek-V3, Qwen 2.5, and more.
Create notebook instances, fine-tuning tasks, inferencing, and model serving seamlessly on VNG Cloud Portal.
A flexible AI model environment with auto-scaling capabilities, enabling seamless deployment of large and complex models.
Optimized GPU configurations for AI/ML workloads, including HGX H100, RTX 4090, L40S, A40, and InfiniBand network.
Easily deploy and optimize model performance with multi-models.
Pay only for the infrastructure, storage, and model usage with a flexible pay-as-you-go pricing model.
Optimized performance, robust security, and cost efficiency!
Deploy a complete AI model on VNG Cloud Portal in just minutes.
Save up to 70% of resources compared to self-deployment.
GPU infrastructure is always available and optimized for all AI workloads.
High-availability resources ensure seamless scalability to meet business demands anytime.
With data centers located in Vietnam, VNG Cloud fully complies with government regulations on data sovereignty, ensuring businesses operate securely within the legal framework.
