DGX Spark x4 vs RTX 3090 x8 Board Value Matrix Compare Best sourced output tok/s per model (single-stream generation) — engine and version, quantization, context and a source link on every row. Hover a value for the quant.
DGX Spark x4 9 sourced runs · best 124.0 tok/s
RTX 3090 x8 4 verified runs · best 91.2 tok/s
Model DGX Spark x4 RTX 3090 x8 GLM-5.3-Flash 124.0 EXL3 4bpw 75.2 AWQ-4bit DeepSeek-V4-Flash-0731 — 91.2 FP8_E4M3 DeepSeek-V4.1-Flash 82.0 EXL3 3.5bpw — keys-DeepSeekV4Flash-Vision-EXP-ablit — 66.8 FP8
Head-to-head (models tested on both): DGX Spark x4 1 · RTX 3090 x8 0 · tied 0 · data as of Oct 12, 2026. Full rules: methodology .
Related reading: RTX 5090 vs 3090 · quantization · Value index · Full board