krea models
2 krea models on Hugging Face, from 12.8B to 12.8B parameters. The cheapest way to run Krea-2-Raw is $0.338/hr.
krea models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| Krea-2-Raw | 12.8B | BF16 | 28.7 GB | RTX 4080 Super | $0.338/hr |
| Krea-2-Turbo | 12.8B | BF16 | 28.7 GB | RTX 4080 Super | $0.338/hr |
VRAM is for the precision the model is published in, with the same overhead and an 8,192-token context assumed on every page; 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.
