Use case

Image generation (Stable Diffusion, Flux, …).

Diffusion training is workstation-friendly; Flux fine-tuning fits on a single 24GB consumer GPU. SDXL inference runs comfortably on 8–12GB VRAM.

≥ 8GB VRAM Consumer tier
Best GPUs

Top GPUs for this workload.

Ranked by suitability — higher fitness scores mean the card handles this workload more comfortably.

GPU Tier VRAM Fit
consumer 32GB 90 Compare →
consumer 24GB 90 Compare →
workstation 48GB 80 Compare →
consumer 16GB 75 Compare →
datacenter 48GB 75 Compare →
datacenter 80GB 70 Compare →
workstation 32GB 70 Compare →
workstation 48GB 70 Compare →
consumer 24GB 70 Compare →
workstation 24GB 65 Compare →
datacenter 24GB 60 Compare →
workstation 16GB 55 Compare →
Best AI models

Top models for this workload.