Aleph-Alpha models
2 Aleph-Alpha models on Hugging Face, from 78.1B to 78.1B parameters. At the precision each one is published in, the smallest needs about 87.3 GB of VRAM (Kolibri-1, cheapest live fit: RTX PRO 6000) and the largest about 175 GB (Kolibri-1-BF16, cheapest live fit: RTX A5000). The cheapest way to run Kolibri-1 is $1.38/hr.
Aleph-Alpha models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| Kolibri-1 | 78.1B | F8_E4M3 | 87.3 GB | RTX PRO 6000 | $1.38/hr |
| Kolibri-1-BF16 | 78.1B | BF16 | 175 GB | RTX A5000 × 8 | $1.41/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.
