Local LLMs
Execute LLMs within a DaDesktop desktop rather than sending prompts to external APIs. The model operates on DaDesktop's GPU infrastructure, ensuring your prompts, files, and other data remain contained within the desktop environment. In this setup, you pay for the desktop resources rather than for each individual token.
Why run LLMs locally
- Keep data private: Your prompts, files, and other data stay within the DaDesktop environment.
- No per-token costs: Utilize DaDesktop's GPU infrastructure to run models without incurring per-request API fees.
- Choose your model: Select the specific model you wish to deploy and manage its configuration.
- Run your own workloads: Deploy the model directly from the desktop alongside other applications and tools.
AI agents
Operate agents that leverage local models to complete tasks and interact with tools.
Coding
Leverage local models for coding assistance, development, and testing.
Research and experimentation
Utilise models for research, analysis, and evaluating different models and configurations.
How it works
Select a DaDesktop GPU desktop, load your model, and run it locally. GPU passthrough provides the desktop with full access to a physical GPU for LLM workloads. 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.