I love small models. I want them to be as tiny as Swiss watch cogs.
But
The mother brain, the queen bee with her huge brain still reins supreme.
Don’t accept this narrative push to make small compute/models the default.
Demand access to supreme VRAM and High-P models!
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.