RTX 5070 12GB

Nvidia · 12 GB VRAM

1recorded run

116.0best tok/s

1sourced

How it compares — 12 GB tier

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 26, 2026. What these labels mean.

GPU	Model	Quant	Backend	Ctx	tok/s	prompt tok/s	VRAM GB	Source
RTX 5070 12GB · 12 GB	Nemotron 3.5 Bolt E4B 4GB	Q4_K_M	llama.cpp b11834	4000	116.0 ✓	—	—	src