naver-hyperclovax models
3 naver-hyperclovax models on Hugging Face, from 3.7B to 33.3B parameters. At the precision each one is published in, the smallest needs about 16.6 GB of VRAM (HyperCLOVAX-SEED-Vision-Instruct-3B, cheapest live fit: RTX A5000) and the largest about 74.5 GB (HyperCLOVAX-SEED-Think-32B, cheapest live fit: A100). The cheapest way to run HyperCLOVAX-SEED-Vision-Instruct-3B is $0.176/hr.
naver-hyperclovax models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| HyperCLOVAX-SEED-Vision-Instruct-3B | 3.7B | F32 | 16.6 GB | RTX A5000 | $0.176/hr |
| HyperCLOVAX-SEED-Think-14B | 14.7B | F32 | 65.9 GB | A100 | $1.21/hr |
| HyperCLOVAX-SEED-Think-32B | 33.3B | BF16 | 74.5 GB | A100 | $1.21/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.
