RTX 3080 vs RTX 3090 x2
Best verified output tok/s per model (single-stream generation). Hover a value for the quant.
RTX 30809 verified runs · best 277.8 tok/s
RTX 3090 x26 verified runs · best 240.8 tok/s
| Model | RTX 3080 | RTX 3090 x2 |
|---|---|---|
| LFM2.5-8B-A1B | 277.8 | — |
| Qwen3.6-27B | — | 240.8 |
| Qwen3.8-27B | 44.4 | 219.8 |
| NVIDIA-Nemotron-3.5-Lightning-30B-A3B | — | 197.0 |
| Ornith-1.5-9B | 82.8 | — |
| Qwen3.8-27B-Uncensored | 74.1 | — |
| Bonsai-27B | 72.9 | — |
| gemma-4-12B-it-qat | 71.2 | — |
| Ornith-1.5-35B-A3B | 64.4 | — |
| gpt-oss-20b | 57.1 | — |
| Qwen3.8-Flash-Next-REAP-256-duo | — | 53.5 |
| Qwen3.8-Flash-Next | — | 40.1 |
| Muse-Glimmer-30B | 6.0 | — |