Press Space to continue
Press Space to continue
People want Claude at home. The reality is that this is not it. Bring those long-horizon agent benchmarks up towards 98% in v3 please! > Headline: 98.2% retained in aggregate > Reality: 75.6% on swe-bench + terminal-bench. https://x.com/casper_hansen_/status/2101…
PrismML@PrismML1d ago
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.
