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.
| Model | Parameters | Native VRAM | FP8 VRAM | INT4 VRAM | Live GPU fit (native) | Est. $/hr | KV cache at 32K |
|---|---|---|---|---|---|---|---|
| Kandinsky-6.0-Pro-5s-Diffusers | 30.1B | 67.4 GB | 33.7 GB | 16.8 GB | A100 | $1.18/hr | not 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)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| Kandinsky-6.0-Pro-5s-Diffusers | 30.1B | BF16 | 67.4 GB | A100 | $1.18/hr |
Fine-tunes and community models (1)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| Kandinsky-6.0-Pro-distill-5s-Diffusers | 30.1B | BF16 | 67.4 GB | A100 | $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.