Local LLMs
Run an LLM inside a DaDesktop desktop instead of sending your prompts to an external API. The model runs on DaDesktop's GPU infrastructure, while your prompts, files, and other data stay within the desktop environment. You pay for the desktop rather than for each token.
Why run LLMs locally
- Keep data private: your prompts, files, and other data stay in the DaDesktop environment.
- No per-token costs: run the model on DaDesktop's GPU infrastructure without paying an API for each request.
- Choose your model: pick the model you want to run and control how it is configured.
- Run your own workloads: use the model directly from the desktop and alongside other applications and tools.
AI agents
Run agents that use local models to complete tasks and work with tools.
Coding
Use local models for coding assistance, development, and testing.
Research and experimentation
Use models for research, analysis, and testing different models and configurations.
How it works
Pick a DaDesktop GPU desktop, load your model, and run it locally. GPU passthrough gives the desktop full access to a physical GPU for LLM workloads. You can compare available GPUs, specs, 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.