inferencerlabs
/

DeepSeek-V3.2-MLX-5.5bit

Text Generation

Model card Files Files and versions

inferencerlabs commited on 10 days ago

Commit

ff1a702

·

verified ·

1 Parent(s): b860849

Upload complete model

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -29,7 +29,7 @@ tags:
 #### M3 Ultra 512GB RAM connected to MBP 128GB RAM using [Inferencer app v1.7.3](https://inferencer.com) with LAN distributed compute
 * Expect ~13.7 tokens/s @ 1000 tokens
-* Memory usage: MBP ~20GB + Mac Studio ~430GB (will be expanded in v1.7.4 to support dynamic splits)
   * More RAM available for larger context window using this method
 ##### Quantized with a modified version of [MLX](https://github.com/ml-explore/mlx) 0.28

 #### M3 Ultra 512GB RAM connected to MBP 128GB RAM using [Inferencer app v1.7.3](https://inferencer.com) with LAN distributed compute
 * Expect ~13.7 tokens/s @ 1000 tokens
+* Example memory usage: MBP ~20GB + Mac Studio ~430GB
   * More RAM available for larger context window using this method
 ##### Quantized with a modified version of [MLX](https://github.com/ml-explore/mlx) 0.28