Apple M5 Max 128GB vs DGX Spark

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.

Apple M5 Max 128GB2 sourced runs · best 144.8 tok/s

DGX Spark52 verified runs · best 86.8 tok/s

Specs and evidence

	Apple M5 Max 128GB	DGX Spark
VRAM	128 GB	128 GB
Sourced runs on the board	2	52
Models measured	1	9
Best output tok/s	144.8 tok/s	86.8 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.

The measured matrix

Model	Apple M5 Max 128GB	DGX Spark
DeepSeek-V4.1-Flash-1017-Sushi-STQ	144.8 4bpw	—
Qwen 3.8 Flash	—	86.8 EXL3 3.05bpw
Qwen3.8-Flash-Next	—	75.7 4.05bpw_h6_ng6
GLM-5.3-Flash	—	64.1 EXL3 2.05 bpw
CYBER-FROST-3.8	—	60.7 EXL3
Qwen3.8-Flash-Next-hibrid48	—	60.0 NVFP4 (output head)
Qwen3.8-27B	—	56.0 NVFP4 W4A4
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B	—	48.0 NVFP4
DeepSeek-V4.1-Flash	—	47.0 FP4
Underdog-Saluki-27B	—	22.6 IQ2-mix

10 rows · 1 models on Apple M5 Max 128GB, 9 on DGX Spark — no verified overlap yet, each side shows its own bests · data as of Oct 30, 2026. Full rules: methodology.

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