Zamba models
4 Zamba models on Hugging Face, from 1.2B to 7.4B parameters. At the precision each one is published in, the smallest needs about 5.4 GB of VRAM (Zamba2-1.2B-instruct, cheapest live fit: V100) and the largest about 16.4 GB (Zamba2-7B-Instruct, cheapest live fit: RTX A5000). The cheapest way to run Zamba2-1.2B-instruct is $0.088/hr.
Zamba models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| Zamba2-1.2B-instruct | 1.2B | F32 | 5.4 GB | V100 | $0.088/hr |
| Zamba2-2.7B | 2.7B | BF16 | 6.0 GB | RTX 5060 Ti | $0.110/hr |
| Zamba-7B-v1 | 7.2B | BF16 | 16.2 GB | RTX A5000 | $0.176/hr |
| Zamba2-7B-Instruct | 7.4B | BF16 | 16.4 GB | RTX A5000 | $0.176/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.
