Audio8 models
2 Audio8 models on Hugging Face, from 170M to 4.1B parameters. At the precision each one is published in, the smallest needs about 0.4 GB of VRAM (Audio8-TTS-Preview-0.1b, cheapest live fit: RTX 3060) and the largest about 9.1 GB (ARK-ASR-3B, cheapest live fit: RTX 3060). The cheapest way to run Audio8-TTS-Preview-0.1b is $0.110/hr.
Audio8 models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| Audio8-TTS-Preview-0.1b | 170M | BF16 | 0.4 GB | RTX 3060 | $0.110/hr |
| ARK-ASR-3B | 4.1B | BF16 | 9.1 GB | RTX 3060 | $0.110/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.
