facebook models
3 facebook models on Hugging Face, from 303M to 2.3B parameters. At the precision each one is published in, the smallest needs about 1.4 GB of VRAM (dinov3-vitl16-pretrain-lvd1689m, cheapest live fit: V100) and the largest about 10.3 GB (seamless-m4t-v2-large, cheapest live fit: V100). The cheapest way to run dinov3-vitl16-pretrain-lvd1689m is $0.088/hr.
facebook models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| dinov3-vitl16-pretrain-lvd1689m | 303M | F32 | 1.4 GB | V100 | $0.088/hr |
| sam3 | 860M | F32 | 3.8 GB | V100 | $0.088/hr |
| seamless-m4t-v2-large | 2.3B | F32 | 10.3 GB | V100 | $0.088/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 Meta
- Wav2Vec 2.0 (32 models)
- MMS (3 models)
