llamaperf
Submit

RTX 4090 vs RTX 5060 Ti 16GB

For running local LLMs · 45 reports across 7 models

Side A
RTX 4090
Vendor
nvidia
VRAM
24GB
Memory
Discrete
Side B
RTX 5060 Ti 16GB
Vendor
nvidia
VRAM
16GB
Memory
Discrete

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 →

ModelRTX 4090RTX 5060 Ti 16GB
Qwen3.8up to 2400B134.0n=776.7n=17
Qwen3.6up to 35B80.0n=252.2n=6
DeepSeek V4 Flashup to 285B180.0n=611.0n=1
Gemma 4up to 31B149.6n=273.9n=1
Museup to 30B—18.0n=1
Ornith1.5up to 35B—105.0n=1
Qwen3up to 235B—52.0n=1

More comparisons