spicyneuron
/

MiniMax-M2.7-MLX-4.9bit

Text Generation

4-bit precision

Model card Files Files and versions

spicyneuron commited on about 14 hours ago

Commit

5f69518

·

verified ·

1 Parent(s): 353e5e7

Update README.md

Files changed (1) hide show

README.md +3 -2

README.md CHANGED Viewed

@@ -10,8 +10,9 @@ base_model: MiniMaxAI/MiniMax-M2.7
 ---
 [MiniMax-M2.7](MiniMaxAI/MiniMax-M2.7) optimized for MLX.
-A mixed-precision quant that balances speed, memory, and accuracy.
-4 bit baseline with important layers at 5, 6, 8, and BF16.
 # Usage

 ---
 [MiniMax-M2.7](MiniMaxAI/MiniMax-M2.7) optimized for MLX.
+- A mixed-precision quant that balances speed, memory, and accuracy.
+- 4 bit baseline with important layers at 5, 6, 8, and BF16.
 # Usage