CMP 170HX vs RX 7900 XTX

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.

CMP 170HX16 sourced runs · best 255.9 tok/s

RX 7900 XTX6 verified runs · best 550.2 tok/s

Specs and evidence

	CMP 170HX	RX 7900 XTX
VRAM	64 GB	24 GB
Sourced runs on the board	16	6
Models measured	11	5
Best output tok/s	255.9 tok/s	550.2 tok/s
Highest measured peak VRAM	58.7 GB	22.9 GB
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.

Head-to-head

On the 2 models measured on both cards, CMP 170HX leads on 1, RX 7900 XTX on 1. The widest gap is on Qwen3.6-35B-A3B: CMP 170HX 87.2 tok/s vs RX 7900 XTX 150.0 tok/s (RX 7900 XTX 72% faster).

The measured matrix

Model	CMP 170HX	RX 7900 XTX
Qwen3.5-0.8B	—	550.2 MQ4
LFM2.5-350M	—	398.4 MQ4
Qwen3.8-27B	255.9 W4A16	154.2 MQ4
NVIDIA-Nemotron-3.5-Lightning-30B-A3B	165.1 Q8_0	—
Qwen3.6-35B-A3B	87.2 UD-Q8_K_XL	150.0 MQ4R
Ornith-1.5-35B-A3B	87.1 Q8_0	—
Qwen3.6-35B-A3B-abliterated-v4	—	82.1 Q8_0
Ornith-1.5-9B	61.5 BF16	—
Qwen3.8-27B-MTP	46.4 INT8-W8A16	—
Qwen3.8-Flash-Next	46.1 UD-IQ1_S	—
Llama-4-Scout-17B-16E-Instruct	44.5 UD-Q3_K_XL	—
gemma-4-31B-it	28.3 NVFP4	—
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 1 · RX 7900 XTX 1 · tied 0 · data as of Oct 30, 2026. Full rules: methodology.

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