Compare Runtimes

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

MetricGGUFCUDA RuntimeVulkan
ScoreA-83B-65C+64
Type
Executionaotaotaot
Interfaceembeddedsdksdk
Cold Start<1ms100ms100ms
Memory0MB500MB200MB
Startup<1ms50ms30ms
Isolationprocesshardwarehardware
Maturityproductionproductionproduction
LanguagesAnyC, C++, PythonC, C++
LicenseMITProprietaryApache-2.0
Links