Local LLMs

Host your Large Language Model (LLM) directly within a DaDesktop environment, eliminating the need to route prompts to external APIs. The model operates on DaDesktop's GPU infrastructure, ensuring that your prompts, files, and data remain securely contained within the desktop. This approach allows you to pay for the desktop resource itself rather than incurring per-token costs.

Benefits of running LLMs locally

AI agents

Deploy agents that leverage local models to execute tasks and interact with various tools.

Coding

Leverage local models to assist with coding, development workflows, and testing.

Research and experimentation

Utilize models for deep research, data analysis, and the evaluation of different configurations.

How it works

Select a DaDesktop GPU instance, load your chosen model, and launch it locally. GPU passthrough provides the desktop with exclusive access to a physical GPU, optimized for LLM workloads. You can review available GPUs, their specifications, and supported configurations on the GPU page.

Start Your Free Trial Today

Run seamless virtual IT training with cloud-based labs, no downtime, just scalable learning that works.