Local LLMs
Execute an LLM within a DaDesktop desktop environment, bypassing the need to send prompts to external APIs. The model operates on DaDesktop's GPU infrastructure, ensuring that your prompts, files, and other data remain securely within the desktop environment. This approach involves paying for the desktop resource rather than per-token usage.
Why run LLMs locally
- Maintain data privacy: Your prompts, files, and data remain contained within the DaDesktop environment.
- Eliminate per-token costs: Leverage DaDesktop's GPU infrastructure to run models without incurring API fees per request.
- Select your model: Choose the specific model you wish to run and retain full control over its configuration.
- Execute custom workloads: Utilize the model directly from the desktop, integrating seamlessly with other applications and tools.
AI agents
Deploy agents that utilize local models to accomplish tasks and interact with tools.
Coding
Leverage local models for coding assistance, development processes, and testing.
Research and experimentation
Utilize models for research, analysis, and the evaluation of various models and configurations.
How it works
Select a DaDesktop GPU desktop, load your desired model, and execute it locally. GPU passthrough enables the desktop to have full access to a physical GPU for LLM workloads. You can compare 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.