MiniMax M2 models
4 MiniMax M2 models from MiniMax on Hugging Face, from 228.7B to 228.7B parameters, published by MiniMax in F8_E4M3, with contexts from 192K to 200K tokens. The smallest official model, MiniMax-M2, needs about 256 GB of VRAM at its published precision; the cheapest live fit is RTX 4080 Super at $2.88/hr.
Part of the MiniMax series · Previous generation: MiniMax-Text · Next generation: MiniMax M3
Pick a size
One row per official MiniMax M2 size: the VRAM it needs at each precision, the cheapest GPU that holds it today, and the KV cache for a 32K-token context.
| Model | Parameters | Native VRAM | FP8 VRAM | INT4 VRAM | Live GPU fit (native) | Est. $/hr | KV cache at 32K |
|---|---|---|---|---|---|---|---|
| MiniMax-M2.7 | 228.7B | 256 GB | – | 128 GB | RTX 4080 Super × 8 | $2.88/hr | 7.8 GB |
VRAM is weights times a flat 1.2 overhead; the KV cache is a separate per-model figure at 16-bit, shown where the architecture is published. See the methodology.
Official models (4)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| MiniMax-M2 | 228.7B | F8_E4M3 | 256 GB | RTX 4080 Super × 8 | $2.88/hr |
| MiniMax-M2.1 | 228.7B | F8_E4M3 | 256 GB | RTX 4080 Super × 8 | $2.88/hr |
| MiniMax-M2.7 | 228.7B | F8_E4M3 | 256 GB | RTX 4080 Super × 8 | $2.88/hr |
| MiniMax-M2.5 | 228.7B | F8_E4M3 | 256 GB | RTX 4080 Super × 8 | $2.88/hr |
VRAM is for the precision the model is published in: the weights times a flat 1.2 overhead, with the KV cache not included. 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 H3 (6 models)
- MiniMax M3 (4 models)
- MiniMax Music3 (1 models)
- MiniMax-Text (1 models)
