Stable Diffusion 3 models

3 Stable Diffusion 3 models from Stability AI on Hugging Face, from 2.1B to 8.1B parameters, published by Stability AI in F16 and BF16. The smallest official model, stable-diffusion-3-medium-diffusers, needs about 4.7 GB of VRAM at its published precision; the cheapest live fit is RTX 3070 at $0.088/hr.

Part of the Stable Diffusion series · Previous generation: Stable Diffusion XL

Pick a size

One row per official Stable Diffusion 3 size: the VRAM it needs at each precision, the cheapest GPU that holds it today, and the KV cache for a 32K-token context.

ModelParametersNative VRAMFP8 VRAMINT4 VRAMLive GPU fit (native)Est. $/hrKV cache at 32K
stable-diffusion-3-medium-diffusers2.1B4.7 GB2.3 GB1.2 GBRTX 3070$0.088/hrnot published for this architecture
stable-diffusion-3.5-medium2.5B5.5 GB2.8 GB1.4 GBRTX 3070$0.088/hrnot published for this architecture
stable-diffusion-3.5-large8.1B18.2 GB9.1 GB4.6 GBRTX A5000$0.176/hrnot published for this architecture

VRAM is weights times a flat 1.2 overhead; the KV cache is a separate per-model figure at 16-bit, shown where the architecture is published. See the methodology.

Official models (3)

ModelParametersPublished asVRAM neededLive GPU fitEst. $/hr
stable-diffusion-3-medium-diffusers2.1BF164.7 GBRTX 3070$0.088/hr
stable-diffusion-3.5-medium2.5BBF165.5 GBRTX 3070$0.088/hr
stable-diffusion-3.5-large8.1BBF1618.2 GBRTX A5000$0.176/hr

VRAM is for the precision the model is published in: the weights times a flat 1.2 overhead, with the KV cache not included. See the methodology. The fit shown is the lowest-priced single GPU type that holds the model at that precision, or the lowest-priced multi-GPU set (up to 8) when none does.

More from Stability AI

Start ComfyUI on a rented GPU.

© 2026 Aquanode. All rights reserved.

All trademarks, logos and brand names are the property of their respective owners.