bosonai models
2 bosonai models on Hugging Face, from 4.7B to 8.9B parameters. At the precision each one is published in, the smallest needs about 10.4 GB of VRAM (higgs-tts-3-4b, cheapest live fit: RTX 3060) and the largest about 19.9 GB (higgs-audio-v3-8b-stt-v2, cheapest live fit: RTX A5000). The cheapest way to run higgs-tts-3-4b is $0.110/hr.
bosonai models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| higgs-tts-3-4b | 4.7B | BF16 | 10.4 GB | RTX 3060 | $0.110/hr |
| higgs-audio-v3-8b-stt-v2 | 8.9B | BF16 | 19.9 GB | RTX A5000 | $0.176/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.
