sensenova models
2 sensenova models on Hugging Face, from 17.5B to 17.6B parameters. At the precision each one is published in, the smallest needs about 39.2 GB of VRAM (SenseNova-U1.5-8B-MoT, cheapest live fit: RTX A6000) and the largest about 39.2 GB (SenseNova-U1-8B-MoT, cheapest live fit: RTX A6000). The cheapest way to run SenseNova-U1.5-8B-MoT is $0.363/hr.
sensenova models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| SenseNova-U1.5-8B-MoT | 17.5B | BF16 | 39.2 GB | RTX A6000 | $0.363/hr |
| SenseNova-U1-8B-MoT | 17.6B | BF16 | 39.2 GB | RTX A6000 | $0.363/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.
