RTX 5070 12GB + RTX 5060 Ti 16GB x2

Nvidia · 12 GB VRAM

1recorded run

66.0best tok/s

1sourced

How it compares — 12 GB per card · multi-GPU

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

Evidence: 1 sourced run · 1 independent source · first recorded Oct 20, 2026. What these labels mean.

GPU	Model	Quant	Backend	Ctx	tok/s	prompt tok/s	VRAM GB	Source
RTX 5070 12GB + RTX 5060 Ti 16GB x2 · 12 GB	Qwen3.8-Flash-Next	IQ3_S	strata v0.2.0-beta	14000	66.0 ✓	—	—	src