Hy3 models
3 Hy3 models on Hugging Face, from 298.8B to 298.8B parameters. At the precision each one is published in, the smallest needs about 334 GB of VRAM (Hy3-FP8, cheapest live fit: RTX 4090) and the largest about 668 GB (Hy3, cheapest live fit: RTX PRO 6000 WS). The cheapest way to run Hy3-FP8 is $3.09/hr.
Hy3 models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| Hy3 | 298.8B | BF16 | 668 GB | RTX PRO 6000 WS × 7 | $10.48/hr |
| Hy3-preview | 298.8B | BF16 | 668 GB | RTX PRO 6000 WS × 7 | $10.48/hr |
| Hy3-FP8 | 298.8B | F8_E4M3 | 334 GB | RTX 4090 × 7 | $3.09/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 Tencent
- Hy-MT2 (3 models)
