Run 35B MoE models in ~2.5 GB of RAM. Weights stream from SSD; a trained router predicts loads a step ahead. Mac, iPhone, Android, Windows supported
Python
README: use hf-mirror video URL for playback
linyubupa4ffd40af25ba
diff --git a/README.md b/README.mdindex 6f09534..406e3eb 100644--- a/README.md+++ b/README.md@@ -70,7 +70,7 @@ are co-located with each checkpoint and load automatically, so<div align="center"><video- src="https://huggingface.co/Edge0/Edge0-35B-A3B-preview/resolve/main/20260910-105854.mp4"+ src="https://hf-mirror.com/Edge0/Edge0-35B-A3B-preview/resolve/main/20260910-105854.mp4"controlsplaysinlinepreload="metadata"