CMP 170HX vs CMP 170HX x2

Name: CMP 170HX vs CMP 170HX x2
Creator: DiggTop

GPU AGPU B

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

CMP 170HX16 verified runs · best 255.9 tok/s

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

Model	CMP 170HX	CMP 170HX x2
Qwen3.8-27B	255.9 W4A16	—
Qwen3.8-Flash-Next	46.1 UD-IQ1_S	186.9 W4A16-FP8PLE
NVIDIA-Nemotron-3.5-Lightning-30B-A3B	165.1 Q8_0	—
Qwen3.6-35B-A3B	87.2 UD-Q8_K_XL	—
Ornith-1.5-35B-A3B	87.1 Q8_0	—
Laguna-S-2.1	—	63.3 Q4_K_M
Ornith-1.5-9B	61.5 BF16	—
Hy-MT2-30B-A3B	—	61.4 FP8
Qwen3.8-27B-MTP	46.4 INT8-W8A16	—
Llama-4-Scout-17B-16E-Instruct	44.5 UD-Q3_K_XL	—
gemma-4-31B-it	28.3 NVFP4	—
Hy3	—	27.6 Q2_K_XL
Baichuan-M3-235B	—	26.1 Q3_K_M
granite-4.2-30b	23.7 Q8_0	—
Llama-3.3-70B-Instruct	20.1 NVFP4	—

Head-to-head (models tested on both): CMP 170HX 0 · CMP 170HX x2 1 · tied 0 · data as of Sep 25, 2026. Full rules: methodology.