RTX 3090 x2 vs Tesla V100 x2
Best verified output tok/s per model (single-stream generation). Hover a value for the quant.
RTX 3090 x26 verified runs · best 240.8 tok/s
Tesla V100 x25 verified runs · best 96.1 tok/s
| Model | RTX 3090 x2 | Tesla V100 x2 |
|---|
| Qwen3.6-27B | 240.8 AutoRound INT4 | — |
| Qwen3.8-27B | 219.8 AutoRound INT4 + fp8 KV | 24.0 Q8_K_XL |
| NVIDIA-Nemotron-3.5-Lightning-30B-A3B | 197.0 NVFP4 | — |
| Qwen3.8-Flash-Next | 40.1 Unsloth-Dynamic-IQ3_XXS | 96.1 IQ3XXS |
| Ornith-1.5-35B-A3B | — | 65.0 Q4_K_M |
| Qwen3.8-Flash-Next-REAP-256-duo | 53.5 Unsloth-Dynamic-Q3_K_XL | — |
Head-to-head (models tested on both): RTX 3090 x2 1 · Tesla V100 x2 1 · tied 0 · data as of Sep 23, 2026. Full rules: methodology.
Related reading: RTX 5090 vs 3090 · quantization · Value index · Full board