RTX 2080

Nvidia · 8 GB VRAM

2recorded runs

22.9best tok/s

0sourced

How it compares — 8 GB tier

RX 5700 XT273.6 RTX 2060 Super97.1 RTX 3060 Ti64.2

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

Evidence: 0 sourced runs · 2 awaiting review · 1 independent source · first recorded Aug 20, 2026 · last recorded Aug 20, 2026. What these labels mean.

What fits on 8 GB — measured

Model	Quant	Peak VRAM	Headroom
Ornith-1.5-9B	Q4_K_M	6.8 GB	1.2 GB
Qwen3.8-9B-Distill	Q4_K_M	6.8 GB	1.2 GB

Peak process memory recorded by the submitter on this card — evidence of what fit, not a guarantee. Plan with the VRAM calculator.

All benchmarks Compare RTX 2080 →

GPU	Model	Quant	Backend	Ctx	tok/s	prompt tok/s	VRAM GB	Source
RTX 2080 · 8 GB	Ornith-1.5-9B	Q4_K_M	llama.cpp —	131072	22.9 …	292.6	6.8	src
RTX 2080 · 8 GB	Qwen3.8-9B-Distill	Q4_K_M	llama.cpp —	131072	22.9 …	292.4	6.8	src

Related reading: GPU buying guide · used GPUs · Value index · Street prices