Noctus(@noctus91):We basically got a Claude Opus 4.6-level model that can run in 8GB of RAM. Bonsai 2 27B by @PrismML is just 5.9GB and reportedly retains 98%+ of the base model’s performance.

2026.09.18 04:34

We basically got a Claude Opus 4.6-level model that can run in 8GB of RAM. Bonsai 2 27B by @PrismML is just 5.9GB and reportedly retains 98%+ of the base model’s performance.

PrismML@PrismML

2026.09.17 21:03

Today, we’re announcing Ternary Bonsai 2 27B. Based on Qwen3.8 27B, Bonsai 2 27B is 9x smaller than its full-precision counterpart while retaining 98.2% of its aggregate benchmark performance. Two months after the first Bonsai 27B release, the biggest change is quality. The footprint remains 5.9 GB, but the gap to full precision has narrowed materially, with particularly strong gains in agentic coding, multimodal reasoning, and long-horizon tool use. Ternary Bonsai 2 27B is available today under Apache 2.0.