H100 PCIe LLM benchmark

Name: H100 PCIe community LLM benchmarks
Creator: llm-speed
License: https://creativecommons.org/licenses/by/4.0/
Keywords: H100 PCIe, LLM benchmark, tokens per second, decode tok/s, prefill, TTFT

No H100 PCIe LLM benchmarks yet. Be the first to submit a signed, reproducible tok/s run from your own H100 PCIe.

Will it run local LLMs?

No signed H100 PCIe run yet, but its 80GB of VRAM tells you what fits. At 4-bit it comfortably runs models up to about 82B parameters with room for context, and up to roughly 130B with tighter quantization. Check a specific model with the VRAM-fit tool.

No H100 PCIe benchmarks yet.

Run on YOUR hardware to populate this page: pipx install llm-speed && llm-speed bench

$ pipx install llm-speed && llm-speed bench

read the methodology

Common questions about H100 PCIe

Direct Q&A drawn from the runs above: fastest LLM, supported model classes, backend rankings, quantization guidance.

Read the H100 PCIe FAQ →