Ternary Bonsai 2 27B: a 5.9GB open model keeping 98.2% of full-precision performance

ivan_bezdomny · x · 2026-09-18

PrismML announced Ternary Bonsai 2 27B, an Apache 2.0 ternary model based on Qwen3.8 27B that is 9x smaller than its full-precision counterpart while retaining 98.2% of aggregate benchmark performance. Two months after the first Bonsai 27B, the 5.9GB footprint is unchanged but quality improved substantially, with strong gains in agentic coding, multimodal reasoning, and long-horizon tool use. Community reactions claim it nearly matches Opus 4.5 and could run locally on a high-end iPad.

Related event: PrismML's Ternary Bonsai 2 27B Shrinks to 5.9GB, Retains 98.2% Performance(20 posts)→

Original post →

More from Infra

Infra channel →