RTX 5080 vs RTX 5090

For running local LLMs · 13 reports across 4 models

Side A

Vendor: nvidia
VRAM: 16GB
Memory: Discrete

Side B

Vendor: nvidia
VRAM: 32GB
Memory: Discrete

Tokens per second by model

Model	RTX 5080	RTX 5090
Qwen3.6up to 35B	56.0n=1	3238.0n=7
Gemma 4up to 31B	—	578.0n=3
Kimi K2.6	—	—n=1
Qwen2.5	—	—n=1

More comparisons