CMP 170HX x10 vs CMP 170HX x4

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 x101 sourced run · best 29.7 tok/s

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

Specs and evidence

	CMP 170HX x10	CMP 170HX x4
VRAM	64 GB	64 GB
Sourced runs on the board	1	2
Models measured	1	2
Best output tok/s	29.7 tok/s	264.6 tok/s
Highest measured peak VRAM	—	—
Street price (latest snapshot)	—	—

Sourced rows only. Peak VRAM is recorded by the person who ran the benchmark, so it is a floor for what the card can hold, not a specification. Price snapshots.

The measured matrix

Model	CMP 170HX x10	CMP 170HX x4
GLM-5.3-Flash	—	264.6 W4A16
DeepSeek-V4-Flash-0731	—	92.1 FP8
GLM-5.2	29.7 INT4-INT8-Mix	—

3 rows · 1 models on CMP 170HX x10, 2 on CMP 170HX x4 — no verified overlap yet, each side shows its own bests · data as of Oct 17, 2026. Full rules: methodology.

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