Granite 4 models
21 Granite 4 models on Hugging Face, from 352M to 32.2B parameters. At the precision each one is published in, the smallest needs about 0.8 GB of VRAM (granite-4.0-350m, cheapest live fit: RTX 5060 Ti) and the largest about 72.0 GB (granite-4.0-h-small, cheapest live fit: A100). The cheapest way to run granite-4.0-350m is $0.110/hr.
Granite 4 models
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.
