MiniMaxAI.MiniMax-M2-GGUF
275 downloads
15 likes
on Hugging Face
updated
Model card
'Make knowledge free for everyone'
Experimental, based on: https://github.com/ggml-org/llama.cpp/pull/16831
Quantized version of: MiniMaxAI/MiniMax-M2
Hexagon test 0 Shot with Q4_K_M
| Model |
Perplexity (PPL) |
± Error |
| Minimax IQ1_M |
11.8447 |
0.21162 |
| Minimax IQ2_XXS |
9.1211 |
0.15936 |
| Minimax Q2_K |
7.6598 |
0.13421 |
| Minimax Q3_K |
6.7349 |
0.11651 |
| Minimax Q4_K_M |
6.5625 |
0.11302 |
