Local LLMs
Execute a Large Language Model (LLM) directly within a DaDesktop environment, eliminating the need to transmit prompts to external APIs. The model operates on DaDesktop’s dedicated GPU infrastructure, ensuring that your prompts, files, and other data remain entirely within the desktop environment. In this setup, you are charged for the desktop resource itself rather than on a per-token basis.
Why run LLMs locally
- Ensure data privacy: Your prompts, files, and related data are contained strictly within the DaDesktop environment.
- Eliminate per-token fees: Leverage DaDesktop’s GPU infrastructure to run models without incurring API charges for each individual request.
- Model flexibility: Select the specific model you wish to utilize and maintain full control over its configuration.
- Execute custom workloads: Deploy the model directly from the desktop, allowing it to run alongside other applications and tools seamlessly.
AI agents
Deploy agents that utilize local models to perform tasks and interact with various tools.
Coding
Leverage local models to support coding tasks, software development, and testing workflows.
Research and experimentation
Utilize models for in-depth research, data analysis, and the testing of different model architectures and configurations.
How it works
Select a GPU-equipped DaDesktop instance, load your chosen model, and run it locally. Thanks to GPU passthrough, the desktop gains full access to a physical GPU specifically 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.