CMP 170HX x2 vs Multi-GPU x3

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 x24 verified runs · best 63.3 tok/s

Multi-GPU x34 verified runs · best 63.3 tok/s

Model	CMP 170HX x2	Multi-GPU x3
Laguna-S-2.1	63.3 Q4_K_M	23.9 UD-IQ4_XS
Qwen3.6-35B-A3B	—	63.3 APEX-I-Balanced
Hy-MT2-30B-A3B	61.4 FP8	—
Qwen3.6-27B	—	60.3 Q6_K_L
Ling-3.0-flash	—	43.4 AD-IQ4_XXS
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 · Multi-GPU x3 0 · tied 0 · data as of Sep 23, 2026. Full rules: methodology.

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