DGX Spark vs M1 Max 32GB

For running local LLMs · 2 reports across 2 models

Side A

Vendor: nvidia
VRAM: 128GB
Memory: Unified

Side B

Vendor: apple
VRAM: 32GB
Memory: Unified

Tokens per second by model

Model	DGX Spark	M1 Max 32GB
GLM-5.1	—n=1	—
Gemma 4up to 31B	—	10.0n=1

More comparisons