RTX 3090 x2 vs Tesla V100 PCIe 16GB

GPU AGPU B

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.

RTX 3090 x26 sourced runs · best 240.8 tok/s

Tesla V100 PCIe 16GB1 verified run · best 40.7 tok/s

Model	RTX 3090 x2	Tesla V100 PCIe 16GB
Qwen3.6-27B	240.8 AutoRound INT4	—
Qwen3.8-27B	219.8 AutoRound INT4 + fp8 KV	—
NVIDIA-Nemotron-3.5-Lightning-30B-A3B	197.0 NVFP4	—
Qwen3.8-Flash-Next-REAP-256-duo	53.5 Unsloth-Dynamic-Q3_K_XL	—
Qwen3.8-Flash-Next	40.1 Unsloth-Dynamic-IQ3_XXS	40.7 Q2_0

Head-to-head (models tested on both): RTX 3090 x2 0 · Tesla V100 PCIe 16GB 1 · tied 0 · data as of Oct 11, 2026. Full rules: methodology.

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