Local LLMs
Execute an LLM within a DaDesktop desktop environment, eliminating the need to transmit prompts to external APIs. The model operates on DaDesktop's GPU infrastructure, ensuring your prompts, files, and data remain securely contained within the desktop. This approach shifts the cost model from per-token billing to a simple desktop rental fee.
Why run LLMs locally
- Enhance data privacy: All prompts, files, and data are kept strictly within the DaDesktop environment.
- Eliminate per-token costs: Utilise DaDesktop's GPU infrastructure without incurring API fees for individual requests.
- Curate your model selection: Select the specific model required and maintain full control over its configuration.
- Manage custom workloads: Deploy the model directly from the desktop, integrating it seamlessly with other applications and tools.
AI agents
Deploy agents that leverage local models to execute tasks and interact with various tools.
Coding
Utilise local models to support coding assistance, development workflows, and testing processes.
Research and experimentation
Employ models for in-depth research, analysis, and the evaluation of diverse models and configurations.
How it works
Select a DaDesktop GPU desktop, load your chosen model, and execute it locally. GPU passthrough provides the desktop with direct, full 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.