Run Qwen3 8B on a GPU

Needs 7.5 GiB of VRAM or more. A general chat and reasoning model.

Deploy Qwen3 8B

GPUs that fit

GPU	VRAM	Versions
RTX 2080	8 GiB	1
RTX 3070	8 GiB	1
RTX 4060	8 GiB	1
RTX 3080	10 GiB	1
RTX 2080 Ti	11 GiB	2
RTX 3060	12 GiB	2
RTX 4070	12 GiB	2
RTX 4070 Ti	12 GiB	2
RTX 4080	16 GiB	2
A10	24 GiB	2
A30	24 GiB	2
L4	24 GiB	2
RTX 3090	24 GiB	2
RTX 4090	24 GiB	2
A100 40GB	40 GiB	2
A40	48 GiB	2
L40	48 GiB	2
A100 80GB	80 GiB	2
H100 80GB	80 GiB	2

Other models