Update README.md

Files changed (1) hide show

README.md CHANGED Viewed

@@ -30,7 +30,7 @@ Built for **Apple Silicon** with Metal acceleration.
 ## Requirements
 Runs on: Apple Silicon (M1 and higher) with macOS ≥ 13.5 via MLX (Metal).
 Not supported: Intel macOS / Linux / Windows (use a GGUF build + llama.cpp instead).
-Suggested RAM: 48 GB for Q6 gs=32 (works on 32 GB with smaller KV cache).
 ## How to use (MLX)

 ## Requirements
 Runs on: Apple Silicon (M1 and higher) with macOS ≥ 13.5 via MLX (Metal).
 Not supported: Intel macOS / Linux / Windows (use a GGUF build + llama.cpp instead).
+Suggested RAM: 48 GB for Q6 gs=32 (works on 32 GB with slower speeds).
 ## How to use (MLX)