Skip to content
llm-speed

RTX 5090 vs DGX Spark

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

Verdict

DGX Spark 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 DGX Spark and this page fills in the second column automatically.

hardware
RTX 5090
NVIDIA Ada/Blackwell · 32 GB VRAM
View RTX 5090 page →
hardware
DGX Spark
NVIDIA GB10 Grace Blackwell · up to 128 GB unified memory
View DGX Spark page →

RTX 5090 benchmarks — no shared model with DGX Spark yet

See also: RTX 5090 benchmarks · DGX Spark benchmarks · All hardware · All models · Methodology