Tesla V100 x2 vs Tesla V100 x4

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.

Tesla V100 x25 verified runs · best 96.1 tok/s

Tesla V100 x41 verified run · best 391.0 tok/s

Model	Tesla V100 x2	Tesla V100 x4
Qwen3.8-27B	24.0 Q8_K_XL	391.0 NVFP4
Qwen3.8-Flash-Next	96.1 IQ3XXS	—
Ornith-1.5-35B-A3B	65.0 Q4_K_M	—

Head-to-head (models tested on both): Tesla V100 x2 0 · Tesla V100 x4 1 · tied 0 · data as of Sep 23, 2026. Full rules: methodology.

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