DGX Spark x2 vs RTX 3090 x4

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 x233 sourced runs · best 474.0 tok/s

RTX 3090 x41 verified run · best 145.8 tok/s

Specs and evidence

	DGX Spark x2	RTX 3090 x4
VRAM	128 GB	24 GB
Sourced runs on the board	33	1
Models measured	7	1
Best output tok/s	474.0 tok/s	145.8 tok/s
Highest measured peak VRAM	—	—
Street price (latest snapshot)	—	—

Sourced rows only. Peak VRAM is recorded by the person who ran the benchmark, so it is a floor for what the card can hold, not a specification. Price snapshots.

Head-to-head

Only one model has been measured on both cards (Qwen3.8-Flash-Next). On that single data point DGX Spark x2 records 93.0 tok/s and RTX 3090 x4 records 145.8 tok/s — treat it as one data point, not a ranking.

The measured matrix

Model	DGX Spark x2	RTX 3090 x4
Qwen3.8-Flash-Next-hibrid48	474.0 NVFP4 (output head)	—
DeepSeek-V4.1-Flash	154.0 EXL3 2.9bpw	—
Qwen3.8-Flash-Next	93.0 INT4-AutoRound	145.8 W4A16+FP8-KV
DeepSeek-V4.1-Flash-1017	92.8 EXL3 2.9bpw	—
Beam-1.0	58.9 EXL3 3 bpw	—
GLM-5.3-Flash	46.3 NVFP4	—
MiniMax M3.1 Flash	39.4 EXL3 SAGE 2.15 bpw	—

Head-to-head (models tested on both): DGX Spark x2 0 · RTX 3090 x4 1 · tied 0 · data as of Oct 30, 2026. Full rules: methodology.

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