PrismML's Ternary Bonsai 2 27B Shrinks Size 9x, Keeps 98.2% Performance

PrismML released Bonsai 2 27B, a ternary-quantized model using {-1,0,+1} weights that shrinks size 9x while retaining 98.2% performance; its GGUF build is trending on Hugging Face.

2026-09-20 ~ 2026-09-21 · 2 related posts

• Ternary 2-bit Bonsai-2-27B GGUF lands on Hugging Face trending — dealignai · 2026-09-20
• PrismML ships Bonsai 2 27B: 9x smaller ternary model keeps 98.2% of full-precision performance — thione · 2026-09-21