DGX Spark x4 vs RTX PRO 6000 Blackwell x2

GPU AGPU B

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 x49 sourced runs · best 124.0 tok/s

RTX PRO 6000 Blackwell x23 verified runs · best 179.5 tok/s

Model	DGX Spark x4	RTX PRO 6000 Blackwell x2
DeepSeek-V4-Flash-Vision-Exp	—	179.5 FP8
GLM-5.3-Flash	124.0 EXL3 4bpw	159.3 EXL3-3.0bpw
DeepSeek-V4.1-Flash	82.0 EXL3 3.5bpw	—

Head-to-head (models tested on both): DGX Spark x4 0 · RTX PRO 6000 Blackwell x2 1 · tied 0 · data as of Oct 12, 2026. Full rules: methodology.

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