Pythia models
15 Pythia models on Hugging Face, from 213M to 12.0B parameters. At the precision each one is published in, the smallest needs about 0.5 GB of VRAM (pythia-160m, cheapest live fit: V100) and the largest about 26.8 GB (pythia-12b, cheapest live fit: V100). The cheapest way to run pythia-160m is $0.088/hr.
Pythia models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| pythia-160m | 213M | F16 | 0.5 GB | V100 | $0.088/hr |
| pythia-160m-deduped | 213M | F16 | 0.5 GB | V100 | $0.088/hr |
| pythia-160m-seed1 | 213M | F16 | 0.5 GB | V100 | $0.088/hr |
| pythia-160m-seed2 | 213M | F16 | 0.5 GB | V100 | $0.088/hr |
| pythia-160m-seed3 | 213M | F16 | 0.5 GB | V100 | $0.088/hr |
| pythia410m-sft-tldr | 405M | F32 | 1.8 GB | V100 | $0.088/hr |
| pythia-410m | 506M | F16 | 1.1 GB | V100 | $0.088/hr |
| pythia-410m-deduped | 506M | F16 | 1.1 GB | V100 | $0.088/hr |
| pythia-1b | 1.1B | F16 | 2.4 GB | V100 | $0.088/hr |
| pythia-1b-deduped | 1.1B | F16 | 2.4 GB | V100 | $0.088/hr |
| pythia-1.4b-deduped | 1.4B | F32 | 6.3 GB | V100 | $0.088/hr |
| pythia-1.4b | 1.5B | F16 | 3.4 GB | V100 | $0.088/hr |
| pythia-2.8b | 2.9B | F16 | 6.5 GB | V100 | $0.088/hr |
| pythia-6.9b | 7.0B | F16 | 15.6 GB | V100 | $0.088/hr |
| pythia-12b | 12.0B | F16 | 26.8 GB | V100 | $0.187/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.
More from EleutherAI
- GPT-Neo (3 models)
