Local AI
Inspect inference environments, prepare model artifacts, experiment with conversion and estimate costs.
Repositories for this capability
Choose an implementation and open its source and README to get started.
zixcel-local-inferencePrepare and verify local model artifacts before a caller starts a managed inference runtime.devinoExperiment with model conversion and local inference setup before adopting a verified feature in another tool.intel-gpu-wsl-advisorCheck an Intel GPU and WSL environment and see which setup requirements need attention.zixcel-costCalculate an inference-cost estimate from explicit usage and price inputs.
Read the setup instructions
Each repository README describes prerequisites, interfaces and examples.
Explore other capabilities
Browse related capabilities and the full library.