Views
No views yet
MiniMaxAI/MiniMax-M2.5, created with llama.cpp.| Property | Value |
|---|---|
| Base model | MiniMaxAI/MiniMax-M2.5 |
| Architecture | Mixture of Experts (MoE) |
| Total parameters | 230B |
| Active parameters | 10B per token |
| Layers | 62 |
| Total experts | 256 |
| Active experts per token | 8 |
| Source precision | FP8 (float8_e4m3fn) |
| Quantization | Size | Description |
|---|---|---|
| Q6_K | 175 GB | 6-bit K-quant, strong quality/size balance |
llama.cpp and compatible frontends.1# Example with llama-cli
2llama-cli -m MiniMax-M2.5.Q6_K.gguf -p "Hello" -n 128float8_e4m3fn) precision.MiniMaxAI/MiniMax-M2.5 weights.