kandinskylab models

2 kandinskylab models from kandinskylab on Hugging Face, from 30.1B to 30.1B parameters, published by kandinskylab in BF16. The smallest official model, Kandinsky-6.0-Pro-5s-Diffusers, needs about 67.4 GB of VRAM at its published precision; the cheapest live fit is A100 at $1.18/hr.

Pick a size

One row per official kandinskylab 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
Kandinsky-6.0-Pro-5s-Diffusers30.1B67.4 GB33.7 GB16.8 GBA100$1.18/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 (1)

ModelParametersPublished asVRAM neededLive GPU fitEst. $/hr
Kandinsky-6.0-Pro-5s-Diffusers30.1BBF1667.4 GBA100$1.18/hr

Fine-tunes and community models (1)

ModelParametersPublished asVRAM neededLive GPU fitEst. $/hr
Kandinsky-6.0-Pro-distill-5s-Diffusers30.1BBF1667.4 GBA100$1.18/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.

Start ComfyUI on a rented GPU.

© 2026 Aquanode. All rights reserved.

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