DGX Spark x4 vs Mac Studio M3 Ultra

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

Mac Studio M3 Ultra1 verified run · best 78.0 tok/s

Model	DGX Spark x4	Mac Studio M3 Ultra
GLM-5.3-Flash	124.0 EXL3 4bpw	78.0 4-bit
DeepSeek-V4.1-Flash	82.0 EXL3 3.5bpw	—

Head-to-head (models tested on both): DGX Spark x4 1 · Mac Studio M3 Ultra 0 · tied 0 · data as of Oct 12, 2026. Full rules: methodology.

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