llamaperf

RTX 5080 vs V100 32GB

For running local LLMs · 9 reports across 2 models

Side A
RTX 5080
Vendor
nvidia
VRAM
16GB
Memory
Discrete
Side B
V100 32GB
Vendor
nvidia
VRAM
32GB
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 5080V100 32GB
Qwen3.8up to 2400B75.0n=465.7n=2
Qwen3.6up to 35B60.0n=282.0n=1

More comparisons