RTX 3090 x2 vs RTX 4090

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.

RTX 3090 x26 verified runs · best 240.8 tok/s

RTX 40902 verified runs · best 141.2 tok/s

Model	RTX 3090 x2	RTX 4090
Qwen3.6-27B	240.8 AutoRound INT4	—
Qwen3.8-27B	219.8 AutoRound INT4 + fp8 KV	91.6 UD-Q4_K_XL
NVIDIA-Nemotron-3.5-Lightning-30B-A3B	197.0 NVFP4	—
Qwen 3.8 27B	—	141.2 int4 (output head only)
Qwen3.8-Flash-Next-REAP-256-duo	53.5 Unsloth-Dynamic-Q3_K_XL	—
Qwen3.8-Flash-Next	40.1 Unsloth-Dynamic-IQ3_XXS	—

Head-to-head (models tested on both): RTX 3090 x2 1 · RTX 4090 0 · tied 0 · data as of Sep 23, 2026. Full rules: methodology.

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