RTX 3090 vs RTX 5090 x2
Best verified output tok/s per model (single-stream generation). Hover a value for the quant.
RTX 309016 verified runs · best 709.5 tok/s
RTX 5090 x21 verified run · best 195.6 tok/s
| Model | RTX 3090 | RTX 5090 x2 |
|---|
| LFM2.5-1.2B-Instruct | 709.5 Q4_K_M | — |
| Qwen3.5-0.8B-MTP | 476.1 Q6_K_XL | — |
| NVIDIA-Nemotron-3.5-Lightning-30B-A3B | 353.7 NVFP4 | — |
| LFM2.5-2.6B | 305.6 Q4_K_M | — |
| Qwen3.5-4B-MTP | 240.4 Q6_K_XL | — |
| Qwen3.8-27B | 164.6 EXL3-3.5bpw | 195.6 NVFP4 |
| Qwen3.5-9B-MTP | 164.3 Q6_K_XL | — |
| Qwen/Qwen3.8-27B | 136.8 AWQ-INT4 W4A16 | — |
| Qwen3.8-Flash-Next | 38.6 EXL3 2.50bpw | — |
| Ornstein3.6-27B-MTP-NSC-ACE-SABER | 32.9 Q4_K_M | — |
Head-to-head (models tested on both): RTX 3090 0 · RTX 5090 x2 1 · tied 0 · data as of Sep 23, 2026. Full rules: methodology.
Related reading: RTX 5090 vs 3090 · quantization · Value index · Full board