MiniMaxAI models
2 MiniMaxAI models on Hugging Face, from 2.4B to 33.1B parameters. At the precision each one is published in, the smallest needs about 10.9 GB of VRAM (MiniMax-Music3, cheapest live fit: V100) and the largest about 74.0 GB (MiniMax-H3, cheapest live fit: A100). The cheapest way to run MiniMax-Music3 is $0.088/hr.
MiniMaxAI models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| MiniMax-Music3 | 2.4B | F32 | 10.9 GB | V100 | $0.088/hr |
| MiniMax-H3 | 33.1B | BF16 | 74.0 GB | A100 | $1.31/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 MiniMax
- MiniMax M2 (4 models)
- MiniMax M3 (4 models)
