RTX 3090 vs RTX 5060 Ti 16GB
For running local LLMs · 118 reports across 14 models
Highest reported generation speed by model family
These maxima come from different community setups. Model size, quantization, GPU count, offloading and concurrency may differ. They do not establish which GPU is faster for the same workload. Check the comparison conditions →
| Model | RTX 3090 | RTX 5060 Ti 16GB |
|---|---|---|
| Qwen3.8up to 2400B | 382.0n=56 | 76.7n=17 |
| Qwen3.6up to 35B | 170.7n=13 | 52.2n=6 |
| DeepSeek V4 Flashup to 285B | 60.0n=9 | 11.0n=1 |
| GLM-5.2up to 744B | 7.3n=2 | — |
| GLM-5.3up to 321B | 55.0n=2 | — |
| Museup to 30B | 94.0n=1 | 18.0n=1 |
| Qwen2.5up to 32B | 70.0n=2 | — |
| Qwen3up to 235B | 7.5n=1 | 52.0n=1 |
| DeepSeek R1 | 2.0n=1 | — |
| DeepSeek V3 | —n=1 | — |
| DeepSeek V4up to 284B | 15.0n=1 | — |
| GLM-4.5-Airup to 106B | —n=1 | — |
| Gemma 4up to 31B | — | 73.9n=1 |
| Ornith1.5up to 35B | — | 105.0n=1 |