inferencerlabs
/

DeepSeek-V3.2-Speciale-MLX-5.5bit

Text Generation

Model card Files Files and versions

inferencerlabs commited on 2 days ago

Commit

718faee

·

verified ·

1 Parent(s): b6f5844

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -22,7 +22,7 @@ pipeline_tag: text-generation
 #### M3 Ultra 512GB RAM using [Inferencer app v1.7.3](https://inferencer.com)
 * Expect ~16.5 tokens/s @ 1000 tokens
 * Memory usage: ~450 GB
-  * For a larger context window (11k tokens) you can expand the RAM limit:
     ```bash
     sudo sysctl iogpu.wired_limit_mb=507000
     ```

 #### M3 Ultra 512GB RAM using [Inferencer app v1.7.3](https://inferencer.com)
 * Expect ~16.5 tokens/s @ 1000 tokens
 * Memory usage: ~450 GB
+  * For a larger context window (>11k tokens) you can expand the RAM limit:
     ```bash
     sudo sysctl iogpu.wired_limit_mb=507000
     ```