CMP 170HX x2 vs Mac Studio (Mac16,9) with Apple M4 Max

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.

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

CMP 170HX x25 sourced runs · best 186.9 tok/s

Mac Studio (Mac16,9) with Apple M4 Max1 verified run · best 110.3 tok/s

Model	CMP 170HX x2	Mac Studio (Mac16,9) with Apple M4 Max
Qwen3.8-Flash-Next	186.9 W4A16-FP8PLE	110.3 IQ3_XXS + MTP Q8_0
Laguna-S-2.1	63.3 Q4_K_M	—
Hy-MT2-30B-A3B	61.4 FP8	—
Hy3	27.6 Q2_K_XL	—
Baichuan-M3-235B	26.1 Q3_K_M	—

Head-to-head (models tested on both): CMP 170HX x2 1 · Mac Studio (Mac16,9) with Apple M4 Max 0 · tied 0 · data as of Oct 11, 2026. Full rules: methodology.

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