CMP 170HX x4 vs NVIDIA CMP 170HX x2

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 x41 verified run · best 92.1 tok/s

NVIDIA CMP 170HX x21 verified run · best 186.9 tok/s

Model	CMP 170HX x4	NVIDIA CMP 170HX x2
Qwen3.8-Flash-Next-W4A16-FP8PLE	—	186.9 W4A16-FP8PLE
DeepSeek-V4-Flash-0731	92.1 FP8	—

2 rows · 1 models on CMP 170HX x4, 1 on NVIDIA CMP 170HX x2 — no verified overlap yet, each side shows its own bests · data as of Sep 22, 2026. Full rules: methodology.

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