Skip to content
llm-speed

RTX 5090 vs H100 SXM

Signed, community-submitted decode tok/s, prefill, and TTFT for RTX 5090 vs H100 SXM — every number links to the run it came from.

Verdict

H100 SXM has no submitted run yet, so there is no head-to-head number to report. We do have 19 models measured for RTX 5090 (peak 356 tok/s decode on stable-code-instruct-3b) — the table below is that baseline. Run the llm-speed suite on H100 SXM and this page fills in the second column automatically.

hardware
RTX 5090
NVIDIA Ada/Blackwell · 32 GB VRAM
View RTX 5090 page →
hardware
H100 SXM
NVIDIA Hopper · 80 GB VRAM
View H100 SXM page →

RTX 5090 benchmarks — no shared model with H100 SXM yet

See also: RTX 5090 benchmarks · H100 SXM benchmarks · All hardware · All models · Methodology