llamaperf

RTX 2080 Ti vs RTX 4060 Ti 16GB

For running local LLMs · 7 reports across 3 models

Side A
RTX 2080 Ti
Vendor
nvidia
VRAM
11GB
Memory
Discrete
Side B
RTX 4060 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 2080 TiRTX 4060 Ti 16GB
Qwen3.8up to 2400B45.0n=132.5n=4
DeepSeek V4up to 284Bn=1
DeepSeek V4 Flashup to 285B7.4n=1

More comparisons