Skip to content
llm-speed

DGX Spark vs M4 Max

Signed, community-submitted decode tok/s, prefill, and TTFT for DGX Spark vs M4 Max — every number links to the run it came from.

Verdict

DGX Spark has no submitted run yet, so there is no head-to-head number to report. We do have 2 models measured for M4 Max (peak 113 tok/s decode on qwen3-coder-bench-32k) — the table below is that baseline. Run the llm-speed suite on DGX Spark and this page fills in the second column automatically.

hardware
DGX Spark
NVIDIA GB10 Grace Blackwell · up to 128 GB unified memory
View DGX Spark page →
hardware
M4 Max
Apple M4 · up to 128 GB unified memory
View M4 Max page →

M4 Max benchmarks — no shared model with DGX Spark yet

Modeldecode tok/sWorkloadRun
qwen3-coder-bench-32k113.3tok/schat-shortr_roktphpc--8
qwen3-coder109.9tok/sconcurrent-decoder_r0di2hkku1h

See also: DGX Spark benchmarks · M4 Max benchmarks · All hardware · All models · Methodology