CMSManhattan models
2 CMSManhattan models on Hugging Face, from 7.6B to 14.8B parameters. At the precision each one is published in, the smallest needs about 17.0 GB of VRAM (JiRackUltra_7b, cheapest live fit: RTX A5000) and the largest about 33.0 GB (JiRackUltra_14b, cheapest live fit: RTX A6000). The cheapest way to run JiRackUltra_7b is $0.176/hr.
CMSManhattan models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| JiRackUltra_7b | 7.6B | BF16 | 17.0 GB | RTX A5000 | $0.176/hr |
| JiRackUltra_14b | 14.8B | BF16 | 33.0 GB | RTX A6000 | $0.363/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.
