DiggTop

Multi-GPU x3 vs Tesla V100

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.
Multi-GPU x34 verified runs · best 63.3 tok/s
Tesla V1001 verified run · best 4.3 tok/s
ModelMulti-GPU x3Tesla V100
Qwen3.6-35B-A3B63.3 APEX-I-Balanced4.3 Q4_K_M
Qwen3.6-27B60.3 Q6_K_L
Ling-3.0-flash43.4 AD-IQ4_XXS
Laguna-S-2.123.9 UD-IQ4_XS

Head-to-head (models tested on both): Multi-GPU x3 1 · Tesla V100 0 · tied 0 · data as of Sep 23, 2026. Full rules: methodology.

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