Bonsai 2 27B: 9x smaller ternary model keeps 98.2% of benchmarks, runs on a Mac

MaziyarPanahi · x · 2026-09-18

PrismML released Ternary Bonsai 2 27B, built on Qwen3.8 27B with {-1,0,+1} ternary weights and FP16 group-wise scaling (1.76 effective bits/weight). The model is just 5.9GB — over 9x smaller than its full-precision counterpart — while retaining 98.2% of aggregate benchmark performance. It supports 262K context, multimodal image+text input, Apache 2.0 license, with stronger reasoning, coding, vision and agentic capability. One user ran it locally on a Mac Studio to read medication lists in 5.7 seconds.

Related event: PrismML Releases Ternary Bonsai 2 27B: 5.9GB Model Retains 98.2% Performance(14 posts)→

Original post →

More from Infra

Infra channel →