DiggTop

DGX Spark vs DGX Spark x1

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

DGX Spark32 verified runs · best 67.6 tok/s
DGX Spark x13 verified runs · best 72.0 tok/s
ModelDGX SparkDGX Spark x1
Qwen3.8-Flash-Next67.6 EXL3 3.05bpw72.0 EXL3
GLM-5.3-Flash64.1 EXL3 2.05 bpw
Qwen3.8-Flash-Next-hibrid4860.0 NVFP4 (output head)
Qwen3.8-27B56.0 NVFP4 W4A4
Qwen3.8-Flash-Next-NVFP455.0 NVFP4
DeepSeek-V4.1-Flash47.0 FP4

Head-to-head (models tested on both): DGX Spark 0 · DGX Spark x1 1 · tied 0 · data as of Sep 18, 2026. Full rules: methodology.

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