Compare Runtimes

Select runtimes to compare side by side. Click chips below to toggle selection.

MetricPython (CPython)ONNX RuntimeLLM (Python CLI)ExLlamaV2
ScoreB71C-50D49D47
TypeLanguage
Executioninterpretedhybridhybridaot
Interfaceclisdkclisdk
Cold Start50ms500ms500ms1000ms
Memory15MB300MB100MB300MB
Startup10ms100ms100ms200ms
Isolationprocessprocessprocessprocess
Maturityproductionproductionstablestable
LanguagesPythonPython, C++, C#, JavaPythonPython, C++, CUDA
LicenseOtherMITApache-2.0MIT
Links