Access comprehensive model benchmarking
We make it easier to decide when to invest effort in upgrading architectures by providing comparisons against the original model and similar models.
Compare across hardware targets
Easily compare the performance of any model across various cloud CPU and GPU instance types and evaluate the device sizing requirements needed to deploy your models on ARM mobile or embedded processors.
Perform sweeps over the number and types of CPUs to correctly size your cloud or edge CPU instances for maximum cost savings.
Make informed decisions
We show where your model sits across the throughput/latency curve and provide options so you can make an informed choice for what your application needs.