Loading…
Loading…
Models / Krea-2-Turbo-BF16
GPU memory needed (smallest version of each): Krea-2-Turbo-BF16 ~12.8B about 39.4 GB. The cheapest runs on Nvidia A100 from $0.51/h right now.
1 model (~12.8B) · ↓ 20.5K downloads a month · from $0.51/h on Nvidia A100 right now. Each model's versions do the same job; quantized ones (AWQ, FP8, 4-bit) need less GPU memory and run on cheaper machines.
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Originalrootlocalghost/Krea-2-Turbo-BF16 | Diffusers | 35 GB | 39.4 GB | $0.51/h Nvidia A100 |
Model details come from Hugging Face and are refreshed daily; prices follow the live offers. GPU memory is GridPup's estimate: the weights, room for an 8,192-token conversation (chat models) and the runtime's own memory. Large models are split across the GPUs of one machine ("4x RTX 4090").