---
base_model:
- MiniMaxAI/MiniMax-M2.7
---

Minimax 2.7 quants where I tried to extract the maximum performance for my hardware.

This is the similar as AesSedai IQ4_XS quant (and uses the same imatrix) but the down tensors are replaced:

- Q4_K replaces IQ4_XS with Q4_K