Trinity models
3 Trinity models on Hugging Face, from 6.1B to 398.6B parameters. At the precision each one is published in, the smallest needs about 13.7 GB of VRAM (Trinity-Nano-Preview, cheapest live fit: RTX 5060 Ti) and the largest about 891 GB (Trinity-Large-Preview). The cheapest way to run Trinity-Nano-Preview is $0.110/hr.
Trinity models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| Trinity-Nano-Preview | 6.1B | BF16 | 13.7 GB | RTX 5060 Ti | $0.110/hr |
| Trinity-Mini | 26.1B | BF16 | 58.4 GB | A100 | $1.21/hr |
| Trinity-Large-Preview | 398.6B | BF16 | 891 GB | No live fit | – |
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.
