GLiNER models
3 GLiNER models on Hugging Face, from 287M to 486M parameters. At the precision each one is published in, the smallest needs about 1.3 GB of VRAM (GLiNER2.5-multi-Decide, cheapest live fit: V100) and the largest about 2.2 GB (GLiNER2.5-Decide, cheapest live fit: V100). The cheapest way to run GLiNER2.5-multi-Decide is $0.088/hr.
GLiNER models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| GLiNER2.5-multi-Decide | 287M | F32 | 1.3 GB | V100 | $0.088/hr |
| gliner2.5-multi-v1 | 287M | F32 | 1.3 GB | V100 | $0.088/hr |
| GLiNER2.5-Decide | 486M | F32 | 2.2 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.
