Local LLMs

Execute a Large Language Model (LLM) directly within a DaDesktop instance rather than relying on external API calls. While the model utilizes DaDesktop's GPU infrastructure, your prompts, files, and associated data remain secured within the desktop environment. This model involves paying for the desktop instance itself, rather than incurring costs per token.

Benefits of local LLM execution

AI agents

Deploy agents that leverage local models to execute tasks and interact with various tools.

Coding

Leverage local models to support coding assistance, software development, and testing processes.

Research and experimentation

Utilize models for conducting research, performing analysis, and evaluating different models and settings.

Operational workflow

Select a DaDesktop GPU instance, load your desired model, and run it locally. GPU passthrough ensures the desktop has full access to a physical GPU, optimized for LLM tasks. 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.