CMP 170HX x4 vs Mac Studio M3 Ultra

GPU AGPU B

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

Verified data on this pair is thin — most of the board is still pending review. Submit your own run and help fill the matrix: one prompt, three steps, no downloads.

CMP 170HX x42 verified runs · best 264.6 tok/s

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

Model	CMP 170HX x4	Mac Studio M3 Ultra
GLM-5.3-Flash	264.6 W4A16	78.0 4-bit
DeepSeek-V4-Flash-0731	92.1 FP8	—

Head-to-head (models tested on both): CMP 170HX x4 1 · Mac Studio M3 Ultra 0 · tied 0 · data as of Oct 3, 2026. Full rules: methodology.

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