Moondream models
3 Moondream models on Hugging Face, from 1.9B to 9.3B parameters. At the precision each one is published in, the smallest needs about 4.2 GB of VRAM (moondream1, cheapest live fit: V100) and the largest about 20.7 GB (moondream3-preview, cheapest live fit: RTX A5000). The cheapest way to run moondream1 is $0.088/hr.
Moondream models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| moondream1 | 1.9B | F16 | 4.2 GB | V100 | $0.088/hr |
| moondream2 | 1.9B | BF16 | 4.3 GB | RTX 5060 Ti | $0.110/hr |
| moondream3-preview | 9.3B | BF16 | 20.7 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.
