ibm-research models
2 ibm-research models on Hugging Face, from 3.4B to 3.5B parameters. At the precision each one is published in, the smallest needs about 15.1 GB of VRAM (PowerMoE-3b, cheapest live fit: V100) and the largest about 15.7 GB (PowerLM-3b, cheapest live fit: V100). The cheapest way to run PowerMoE-3b is $0.088/hr.
ibm-research models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| PowerMoE-3b | 3.4B | F32 | 15.1 GB | V100 | $0.088/hr |
| PowerLM-3b | 3.5B | F32 | 15.7 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.
