kakaocorp models
2 kakaocorp models on Hugging Face, from 1.3B to 30.7B parameters. At the precision each one is published in, the smallest needs about 2.9 GB of VRAM (kanana-2-1.3b-base, cheapest live fit: RTX 3060) and the largest about 68.6 GB (kanana-2-30b-a3b-instruct-2601, cheapest live fit: A100). The cheapest way to run kanana-2-1.3b-base is $0.110/hr.
kakaocorp models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| kanana-2-1.3b-base | 1.3B | BF16 | 2.9 GB | RTX 3060 | $0.110/hr |
| kanana-2-30b-a3b-instruct-2601 | 30.7B | BF16 | 68.6 GB | A100 | $1.31/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.
