Why not on a CPU with 32 or 64 GB of RAM? | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		phkahler on Aug 1, 2024 \| parent \| context \| favorite \| on: Flux: Open-source text-to-image model with 12B par... Why not on a CPU with 32 or 64 GB of RAM?

holoduke on Aug 1, 2024 | [–]

Much slower memory and limited parallelism. Gpu ÷- 8k pr more cuda cores vs +-16 on regular cpu. Less mem swapping between operations. Gpu much much faster.

CuriouslyC on Aug 1, 2024 | [–]

Performance, mostly. It'll work but image generation is shitty to do slowly compared to text inference.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact