RTX 3090 vs RTX 3090 x2

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.

RTX 309018 sourced runs · best 709.5 tok/s

RTX 3090 x28 verified runs · best 240.8 tok/s

Specs and evidence

	RTX 3090	RTX 3090 x2
VRAM	24 GB	24 GB
Sourced runs on the board	18	8
Models measured	11	7
Best output tok/s	709.5 tok/s	240.8 tok/s
Highest measured peak VRAM	22.0 GB	42.9 GB
Street price (latest snapshot)	$1,720 used	—

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, RTX 3090 leads on 1, RTX 3090 x2 on 2. The widest gap is on NVIDIA-Nemotron-3.5-Lightning-30B-A3B: RTX 3090 353.7 tok/s vs RTX 3090 x2 197.0 tok/s (RTX 3090 80% faster).

The measured matrix

Model	RTX 3090	RTX 3090 x2
LFM2.5-1.2B-Instruct	709.5 Q4_K_M	—
Qwen3.5-0.8B-MTP	476.1 Q6_K_XL	—
NVIDIA-Nemotron-3.5-Lightning-30B-A3B	353.7 NVFP4	197.0 NVFP4
LFM2.5-2.6B	305.6 Q4_K_M	—
Qwen3.6-27B	—	240.8 AutoRound INT4
Qwen3.5-4B-MTP	240.4 Q6_K_XL	—
Qwen3.8-27B	164.6 EXL3-3.5bpw	219.8 AutoRound INT4 + fp8 KV
MiniCPM-V 4.7-35B-A3B	—	172.2 int4
Qwen3.5-9B-MTP	164.3 Q6_K_XL	—
Nanbeige4.3-33B	—	66.2 W4A16 (INT4 AutoRound, GPTQ, gro
Qwen3.8-Flash-Next-REAP-256-duo	—	53.5 Unsloth-Dynamic-Q3_K_XL
Qwen3.8-Flash-Next	38.6 EXL3 2.50bpw	40.1 Unsloth-Dynamic-IQ3_XXS
Ornstein3.6-27B-MTP-NSC-ACE-SABER	32.9 Q4_K_M	—
GLM-5.3-Flash	28.1 EXL3 3.05 bpw	—
DeepSeek-V4.1-Flash	26.0 EXL3 3.0 bpw	—

Head-to-head (models tested on both): RTX 3090 1 · RTX 3090 x2 2 · tied 0 · data as of Oct 30, 2026. Full rules: methodology.

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