nvidia models
2 nvidia models on Hugging Face, from 124M to 8.4B parameters. At the precision each one is published in, the smallest needs about 0.6 GB of VRAM (diar_sortformer_4spk-v1, cheapest live fit: V100) and the largest about 18.7 GB (personaplex-7b-v1, cheapest live fit: RTX A5000). The cheapest way to run diar_sortformer_4spk-v1 is $0.088/hr.
nvidia models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| diar_sortformer_4spk-v1 | 124M | F32 | 0.6 GB | V100 | $0.088/hr |
| personaplex-7b-v1 | 8.4B | BF16 | 18.7 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.
More from NVIDIA
- Parakeet (7 models)
- Nemotron 3 (16 models)
- Cosmos (6 models)
- Nemotron Nano (4 models)
- Nemotron (5 models)
- Nemotron Labs (4 models)
- Nemotron-H (3 models)
