New pricing: More AI power, less cost!
Learn more

Compare GPU Performance on AI Workloads

H100 PCIe
H100 PCIe image
Vs.
A100 PCIe
A100 PCIe image

LLM Benchmarks

Benchmarks were run on RunPod gpus using vllm. For more details on vllm, check out the vllm github repository.
Output Throughput (tok/s)
Get started with RunPod 
today.
We handle millions of gpu requests a day. Scale your machine learning workloads while keeping costs low with RunPod.
Get Started