Granite models
4 Granite models on Hugging Face, from 258M to 3.5B parameters. At the precision each one is published in, the smallest needs about 0.6 GB of VRAM (granite-docling-258M, cheapest live fit: RTX 5060 Ti) and the largest about 7.8 GB (granite-3b-code-base-2k, cheapest live fit: RTX 5060 Ti). The cheapest way to run granite-docling-258M is $0.110/hr.
Granite models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| granite-docling-258M | 258M | BF16 | 0.6 GB | RTX 5060 Ti | $0.110/hr |
| granite-speech-5.0-470m-turboctc | 473M | BF16 | 1.1 GB | RTX 5060 Ti | $0.110/hr |
| granite-speech-5.0-470m-turboctc-nc | 473M | BF16 | 1.1 GB | RTX 5060 Ti | $0.110/hr |
| granite-3b-code-base-2k | 3.5B | BF16 | 7.8 GB | RTX 5060 Ti | $0.110/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.
