DiggTop ⌕

RTX 3090 x2 vs Tesla V100 x4

Pick a different pair →

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 x28 sourced runs · best 240.8 tok/s
Tesla V100 x41 verified run · best 391.0 tok/s

Specs and evidence

RTX 3090 x2Tesla V100 x4
VRAM24 GB16 GB
Sourced runs on the board81
Models measured71
Best output tok/s240.8 tok/s391.0 tok/s
Highest measured peak VRAM42.9 GB61.0 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

Only one model has been measured on both cards (Qwen3.8-27B). On that single data point RTX 3090 x2 records 219.8 tok/s and Tesla V100 x4 records 391.0 tok/s — treat it as one data point, not a ranking.

The measured matrix

ModelRTX 3090 x2Tesla V100 x4
Qwen3.8-27B219.8 AutoRound INT4 + fp8 KV391.0 NVFP4
Qwen3.6-27B240.8 AutoRound INT4—
NVIDIA-Nemotron-3.5-Lightning-30B-A3B197.0 NVFP4—
MiniCPM-V 4.7-35B-A3B172.2 int4—
Nanbeige4.3-33B66.2 W4A16 (INT4 AutoRound, GPTQ, gro—
Qwen3.8-Flash-Next-REAP-256-duo53.5 Unsloth-Dynamic-Q3_K_XL—
Qwen3.8-Flash-Next40.1 Unsloth-Dynamic-IQ3_XXS—

Head-to-head (models tested on both): RTX 3090 x2 0 · Tesla V100 x4 1 · tied 0 · data as of Oct 30, 2026. Full rules: methodology.

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

↑