DGX Spark x4 vs RTX 3090 x1

GPU AGPU B

Best verified output tok/s per model (single-stream generation). Hover a value for the quant.

Verified data on this pair is thin — most of the board is still pending review. Submit your own run and help fill the matrix: one prompt, three steps, no downloads.

DGX Spark x46 verified runs · best 82.0 tok/s

RTX 3090 x12 verified runs · best 28.1 tok/s

Model	DGX Spark x4	RTX 3090 x1
DeepSeek-V4.1-Flash	82.0 EXL3 3.5bpw	26.0 EXL3 3.0 bpw
DeepSeek-V4.1-Flash 552B MoE	41.0 MXFP4	—
GLM-5.3-Flash	—	28.1 EXL3 3.05 bpw

Head-to-head (models tested on both): DGX Spark x4 1 · RTX 3090 x1 0 · tied 0 · data as of Oct 5, 2026. Full rules: methodology.

Related reading: RTX 5090 vs 3090 · quantization · Value index · Full board