Local LLMs
Instead of routing prompts to external APIs, execute LLMs within a DaDesktop desktop environment. This approach leverages DaDesktop's GPU infrastructure to run models, ensuring that your prompts, files, and associated data remain strictly within the desktop. The cost model shifts from paying per token to a flat rate for the desktop instance.
Why run LLMs locally
- Enhance Data Privacy: Keep your prompts, files, and other sensitive data entirely within the DaDesktop ecosystem.
- Eliminate Per-Token Costs: Utilise DaDesktop's GPU resources without incurring fees for each API request.
- Model Autonomy: Select the specific model you wish to deploy and retain full control over its configuration parameters.
- Integrated Workflows: Execute models directly from the desktop, facilitating seamless interaction with other applications and tools.
AI agents
Deploy agents powered by local models to perform tasks and interface with external tools.
Coding
Leverage local models to support coding tasks, software development, and testing processes.
Research and experimentation
Utilise models for analytical research, in-depth analysis, and the evaluation of various configurations and architectures.
How it works
Select a DaDesktop GPU instance, load your chosen model, and initiate local execution. GPU passthrough ensures the desktop has direct access to physical GPU resources, optimised 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.