Very Large GGUFs
Collection
GGUF quantized versions of very large models - over 100B parameters
•
51 items
•
Updated
•
5
'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 |
- Downloads last month
- 4,914
Hardware compatibility
Log In
to view the estimation
1-bit
2-bit
3-bit
4-bit
5-bit
6-bit
8-bit
Model tree for DevQuasar/MiniMaxAI.MiniMax-M2-GGUF
Base model
MiniMaxAI/MiniMax-M2