beipo-ai models
1 beipo-ai model from beipo-ai on Hugging Face, from 396.8B to 396.8B parameters, published by beipo-ai in BF16, with a 256K-token context. The smallest official model, NorthCUA-Pro, needs about 887 GB of VRAM at its published precision.
Pick a size
One row per official beipo-ai 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 |
|---|---|---|---|---|---|---|---|
| NorthCUA-Pro | 396.8B | 887 GB | 443 GB | 222 GB | No live fit | – | 0.94 GB |
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 |
|---|---|---|---|---|---|
| NorthCUA-Pro | 396.8B | BF16 | 887 GB | No live fit | – |
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.
