DiggTop ⌕

DGX Spark x2 vs DGX Spark x4

Pick a different pair →

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 x222 sourced runs · best 474.0 tok/s
DGX Spark x411 verified runs · best 190.0 tok/s

Specs and evidence

DGX Spark x2DGX Spark x4
VRAM128 GB128 GB
Sourced runs on the board2211
Models measured43
Best output tok/s474.0 tok/s190.0 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

On the 2 models measured on both cards, DGX Spark x2 leads on 1, DGX Spark x4 on 1. The widest gap is on GLM-5.3-Flash: DGX Spark x2 46.3 tok/s vs DGX Spark x4 124.0 tok/s (DGX Spark x4 168% faster).

The measured matrix

ModelDGX Spark x2DGX Spark x4
Qwen3.8-Flash-Next-hibrid48474.0 NVFP4 (output head)—
DeepSeek-V4.1-Flash-1017—190.0 EXL3 3.5bpw
DeepSeek-V4.1-Flash154.0 EXL3 2.9bpw82.0 EXL3 3.5bpw
GLM-5.3-Flash46.3 NVFP4124.0 EXL3 4bpw
Qwen3.8-Flash-Next93.0 INT4-AutoRound—

Head-to-head (models tested on both): DGX Spark x2 1 · DGX Spark x4 1 · tied 0 · data as of Oct 17, 2026. Full rules: methodology.

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

↑