Hunyuan models
2 Hunyuan models on Hugging Face, from 7.5B to 80.4B parameters. At the precision each one is published in, the smallest needs about 16.8 GB of VRAM (Hunyuan-7B-Instruct, cheapest live fit: RTX A5000) and the largest about 180 GB (Hunyuan-A13B-Instruct, cheapest live fit: RTX A5000). The cheapest way to run Hunyuan-7B-Instruct is $0.176/hr.
Hunyuan models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| Hunyuan-7B-Instruct | 7.5B | BF16 | 16.8 GB | RTX A5000 | $0.176/hr |
| Hunyuan-A13B-Instruct | 80.4B | BF16 | 180 GB | RTX A5000 × 8 | $1.41/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.
