Ternary Bonsai 2 27B: 5.9GB open model keeps 98.2% of full-precision performance
gajesh · x · 2026-09-18
- PrismML released Ternary Bonsai 2 27B, a ternary-quantized model based on Qwen3.8 27B that is 9x smaller than its full-precision counterpart (5.9GB footprint) while retaining 98.2% of aggregate benchmark performance, under Apache 2.0.
- The biggest change vs. the first Bonsai 27B two months ago is quality, with strong gains in agentic coding, multimodal reasoning, and long-horizon tool use.
- The team says it runs on phones with >8GB RAM and claims it outperforms Opus 4.6 and Luna 5.6; 1,000+ providers on the Darkbloom network can test it immediately.
Related event: PrismML's Ternary Bonsai 2 27B Shrinks to 5.9GB, Retains 98.2% Performance(20 posts)→
More from Models
- Together AI cuts Qwen3.8-Flash pricing 40% for the rest of the month, targeting high-volume coding assistants — togethercompute · 2026-09-29
- Researcher suggests Claude's 'claudish' gibberish may signal Opus communicating beyond human comprehension — JeremyNguyenPhD · 2026-09-29
- Design challenge bonus: Meta Muse almost works but breaks completely on page 3 — NathanWilbanks_ · 2026-09-29
- Late-layer neurons in Qwen act like on-off switches, unlike Olmo — Sauers_ · 2026-09-29
- After a day of real use: Sonnet 5.5 is not just Opus 5.5 at half price — alexcovo_eth · 2026-09-29
- Holo4-27B post-train cuts Qwen3.8-27B agent tokens by 79% on same task — solyarisoftware · 2026-09-29