Local LLMs
Deploy Large Language Models (LLMs) directly within a DaDesktop environment, eliminating the need to route prompts through external APIs. While the model utilizes DaDesktop's GPU resources, your prompts, files, and data remain securely contained within the desktop. This approach shifts the cost model from per-token usage to a flat fee for the desktop instance.
Benefits of running LLMs locally
- Enhanced data privacy: All prompts, files, and sensitive data remain isolated within the DaDesktop environment.
- Predictable costs: Utilize DaDesktop's GPU infrastructure without incurring variable API charges for each request.
- Model flexibility: Select specific models and customize their configuration parameters to suit your needs.
- Integrated workflows: Execute model tasks directly from the desktop, seamlessly alongside other applications and tools.
AI agents
Deploy agents that leverage local models to execute tasks and interact with various tools.
Coding
Leverage local models to assist with software development, coding tasks, and testing processes.
Research and experimentation
Conduct research, perform in-depth analysis, and test various model architectures and configurations.
How it works
Select a DaDesktop GPU instance, load your chosen model, and execute it locally. GPU passthrough ensures the desktop has dedicated access to physical GPU resources for optimized LLM performance. You can review available GPUs, 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.