On-Device LLMs
Execute LLMs within a DaDesktop environment rather than routing prompts to external APIs. The model operates using DaDesktop's GPU resources, ensuring that your prompts, files, and data remain confined to the desktop instance. Billing is based on desktop usage time rather than individual token consumption.
Benefits of local LLM execution
- Enhanced data privacy: Your prompts, files, and associated data are retained entirely within the DaDesktop environment.
- Elimination of per-token fees: Leverage DaDesktop's GPU infrastructure without incurring API charges for every request.
- Model selection flexibility: Select specific models and manage their configurations according to your requirements.
- Custom workload execution: Utilize the model directly within the desktop environment, alongside other applications and tools.
AI agents
Deploy agents that utilize local models to perform tasks and interact with various tools.
Coding
Leverage local models for coding support, development workflows, and testing processes.
Research and experimentation
Employ models for research purposes, data analysis, and evaluating different models and configurations.
Operational overview
Select a DaDesktop GPU instance, load your preferred model, and execute it locally. GPU passthrough ensures the desktop has direct, full access to a physical GPU, optimizing performance for LLM workloads. For details on available GPUs, specifications, and compatible configurations, visit the GPU page.
Start Your Free Trial Today
Run seamless virtual IT training with cloud-based labs, no downtime, just scalable learning that works.