Local LLMs
Execute LLMs within a DaDesktop desktop environment, eliminating the need to transmit prompts to external APIs. By leveraging DaDesktop's GPU infrastructure to host the model, your prompts, files, and data remain securely contained within the desktop. This approach shifts the cost model from per-token API fees to a flat fee for the desktop resource.
Why run LLMs locally
- Preserve data privacy: Ensure that your prompts, files, and other sensitive data remain isolated within the DaDesktop environment.
- Avoid per-token fees: Utilize DaDesktop's GPU infrastructure for model execution without incurring API costs for every individual request.
- Customize your model selection: Select the specific model you require and manage its configuration parameters directly.
- Execute custom workloads: Integrate the model directly into your desktop workflow, allowing it to run alongside other applications and tools.
AI agents
Deploy agents that leverage local models to perform tasks and interact with various tools.
Coding
Leverage local models to support coding assistance, development workflows, and testing procedures.
Research and experimentation
Utilize models for research purposes, data analysis, and the testing of different model architectures and configurations.
How it works
Select a DaDesktop GPU desktop, load your chosen model, and execute it locally. Thanks to GPU passthrough, the desktop gains full access to the physical GPU, optimizing performance 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.