stabilityai models

4 stabilityai models from Stability AI on Hugging Face, from 568M to 1.3B parameters, published by Stability AI in F32. The smallest official model, stable-audio-3-small-sfx, needs about 2.5 GB of VRAM at its published precision; the cheapest live fit is RTX 3070 at $0.088/hr.

Pick a size

One row per official stabilityai 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-audio-3-small-sfx568M2.5 GB0.6 GB0.3 GBRTX 3070$0.088/hrnot published for this architecture
stable-fast-3d1.0B4.5 GB1.1 GB0.6 GBRTX 3070$0.088/hrnot published for this architecture
stable-audio-open-1.01.2B5.4 GB1.4 GB0.7 GBRTX 3070$0.088/hrnot published for this architecture
stable-virtual-camera1.3B5.7 GB1.4 GB0.7 GBRTX 3070$0.088/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 (4)

ModelParametersPublished asVRAM neededLive GPU fitEst. $/hr
stable-audio-3-small-sfx568MF322.5 GBRTX 3070$0.088/hr
stable-fast-3d1.0BF324.5 GBRTX 3070$0.088/hr
stable-audio-open-1.01.2BF325.4 GBRTX 3070$0.088/hr
stable-virtual-camera1.3BF325.7 GBRTX 3070$0.088/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.