syvai models
2 syvai models on Hugging Face, from 335M to 2.1B parameters. At the precision each one is published in, the smallest needs about 0.7 GB of VRAM (plapre-nano, cheapest live fit: RTX 3060) and the largest about 4.6 GB (hviske-v5.3, cheapest live fit: RTX 3060). The cheapest way to run plapre-nano is $0.110/hr.
syvai models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| plapre-nano | 335M | BF16 | 0.7 GB | RTX 3060 | $0.110/hr |
| hviske-v5.3 | 2.1B | BF16 | 4.6 GB | RTX 3060 | $0.110/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.
