Mamba models
3 Mamba models on Hugging Face, from 129M to 2.8B parameters. At the precision each one is published in, the smallest needs about 0.6 GB of VRAM (mamba-130m-hf, cheapest live fit: V100) and the largest about 12.4 GB (mamba-2.8b-hf, cheapest live fit: V100). The cheapest way to run mamba-130m-hf is $0.088/hr.
Mamba models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| mamba-130m-hf | 129M | F32 | 0.6 GB | V100 | $0.088/hr |
| mamba-1.4b-hf | 1.4B | F32 | 6.1 GB | V100 | $0.088/hr |
| mamba-2.8b-hf | 2.8B | F32 | 12.4 GB | V100 | $0.088/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.
