T5 models
3 T5 models on Hugging Face, from 223M to 2.9B parameters. At the precision each one is published in, the smallest needs about 1.0 GB of VRAM (chatgpt_paraphraser_on_T5_base, cheapest live fit: V100) and the largest about 12.7 GB (t5-3b, cheapest live fit: V100). The cheapest way to run chatgpt_paraphraser_on_T5_base is $0.088/hr.
T5 models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| chatgpt_paraphraser_on_T5_base | 223M | F32 | 1.0 GB | V100 | $0.088/hr |
| T5_Paraphrase_Paws | 223M | F32 | 1.0 GB | V100 | $0.088/hr |
| t5-3b | 2.9B | F32 | 12.7 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.
