Whisper models
30 Whisper models on Hugging Face, from 242M to 1.6B parameters. At the precision each one is published in, the smallest needs about 1.1 GB of VRAM (whisper-small.en, cheapest live fit: V100) and the largest about 6.9 GB (whisper-large-v3-ru-podlodka, cheapest live fit: V100). The cheapest way to run whisper-small.en is $0.088/hr.
Whisper 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.
More from OpenAI
- gpt-oss (6 models)
