RTX 5080

Nvidia · 16 GB VRAM

1recorded run

148.3best tok/s

0sourced

How it compares — 16 GB tier

Best verified tok/s per GPU in this VRAM tier — compare any two like-for-like.

Evidence: 0 sourced runs · 1 awaiting review · 1 independent source · first recorded Jun 29, 2026. What these labels mean.

GPU	Model	Quant	Backend	Ctx	tok/s	prompt tok/s	VRAM GB	Source
RTX 5080 · 16 GB	Meta-Llama-3-8B-Instruct	Q4_0	llama.cpp —	4096	148.3 …	8429.6	—	src