Jamba models
3 Jamba models on Hugging Face, from 3.0B to 51.6B parameters. At the precision each one is published in, the smallest needs about 6.8 GB of VRAM (AI21-Jamba2-3B, cheapest live fit: RTX 5060 Ti) and the largest about 115 GB (Jamba-v0.1, cheapest live fit: RTX A5000). The cheapest way to run AI21-Jamba2-3B is $0.110/hr.
Jamba models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| AI21-Jamba2-3B | 3.0B | BF16 | 6.8 GB | RTX 5060 Ti | $0.110/hr |
| AI21-Jamba-Reasoning-3B | 3.2B | BF16 | 7.1 GB | RTX 5060 Ti | $0.110/hr |
| Jamba-v0.1 | 51.6B | BF16 | 115 GB | RTX A5000 × 5 | $0.880/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.
