2 Sep 17 6:34 PM · 8d ago · 1 article · 1 source · development 2 of 4
GIGAZINE reported on the release, noting the model reduces the size of Qwen3.8 27B to 5.9GB while maintaining 98.2% of its performance.
PrismML AI lab, developer of Bonsai modelsBabak Hassibi AI researcher / commenterMiaAI_lab AI lab account
first by GIGAZINE, 8d ago
All 4 developments of PrismML ships Ternary Bonsai 2 27B, a 5.9GB model near… →