Upload README.md with huggingface_hub

README.md

@@ -35,9 +35,9 @@ library_name: mlx
 
 # Kimi-K2.6-Small-JANGTQ
 
-**This is now a ~586B-A32B MoE** (down from Kimi K2.6's ~1T base) —
-aggressive 45% routed-expert prune + 2-bit JANGTQ quantization,
-runnable on a 256 GB Apple Silicon Mac.
+**This is now a ~586B-A32B MoE — 153 GB on disk** (down from Kimi K2.6's
+~610 GB / ~1T base) — aggressive 45% routed-expert prune + 2-bit JANGTQ
+quantization, runnable on a 256 GB Apple Silicon Mac.
 
 - **Source**: [moonshotai/Kimi-K2.6](https://huggingface.co/moonshotai) (Moonshot AI's
   MLA/MoE flagship, INT4 pack-quantized base)