DiggTop ⌕

DGX Spark vs RTX PRO 6000 Blackwell 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 Spark52 sourced runs · best 86.8 tok/s
RTX PRO 6000 Blackwell x49 verified runs · best 231.6 tok/s

Specs and evidence

DGX SparkRTX PRO 6000 Blackwell x4
VRAM128 GB384 GB
Sourced runs on the board529
Models measured91
Best output tok/s86.8 tok/s231.6 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 (DeepSeek-V4.1-Flash). On that single data point DGX Spark records 47.0 tok/s and RTX PRO 6000 Blackwell x4 records 231.6 tok/s — treat it as one data point, not a ranking.

The measured matrix

ModelDGX SparkRTX PRO 6000 Blackwell x4
DeepSeek-V4.1-Flash47.0 FP4231.6 FP4+FP8 native
Qwen 3.8 Flash86.8 EXL3 3.05bpw—
Qwen3.8-Flash-Next75.7 4.05bpw_h6_ng6—
GLM-5.3-Flash64.1 EXL3 2.05 bpw—
CYBER-FROST-3.860.7 EXL3—
Qwen3.8-Flash-Next-hibrid4860.0 NVFP4 (output head)—
Qwen3.8-27B56.0 NVFP4 W4A4—
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B48.0 NVFP4—
Underdog-Saluki-27B22.6 IQ2-mix—

Head-to-head (models tested on both): DGX Spark 0 · RTX PRO 6000 Blackwell x4 1 · tied 0 · data as of Oct 30, 2026. Full rules: methodology.

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

↑