CMP 170HX vs RTX 3080

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

RTX 30809 verified runs · best 277.8 tok/s

Specs and evidence

	CMP 170HX	RTX 3080
VRAM	64 GB	10 GB
Sourced runs on the board	16	9
Models measured	11	9
Best output tok/s	255.9 tok/s	277.8 tok/s
Highest measured peak VRAM	58.7 GB	9.7 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 3 models measured on both cards, CMP 170HX leads on 2, RTX 3080 on 1. The widest gap is on Qwen3.8-27B: CMP 170HX 255.9 tok/s vs RTX 3080 44.4 tok/s (CMP 170HX 476% faster).

The measured matrix

Model	CMP 170HX	RTX 3080
LFM2.5-8B-A1B	—	277.8 Q6_K
Qwen3.8-27B	255.9 W4A16	44.4 IQ2_XXS
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	64.4 Q4_K_M
Ornith-1.5-9B	61.5 BF16	82.8 Q6_K
Qwen3.8-27B-Uncensored	—	74.1 IQ2_XXS
Bonsai-27B	—	72.9 Q1_0
gemma-4-12B-it-qat	—	71.2 Q4_0
gpt-oss-20b	—	57.1 MXFP4
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	—
Muse-Glimmer-30B	—	6.0 Q4_K_M

Head-to-head (models tested on both): CMP 170HX 2 · RTX 3080 1 · tied 0 · data as of Oct 30, 2026. Full rules: methodology.

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