Ternary Bonsai 2 27B: a 5.9GB open model keeping 98.2% of full-precision performance
ivan_bezdomny · x · 2026-09-18
PrismML announced Ternary Bonsai 2 27B, an Apache 2.0 ternary model based on Qwen3.8 27B that is 9x smaller than its full-precision counterpart while retaining 98.2% of aggregate benchmark performance. Two months after the first Bonsai 27B, the 5.9GB footprint is unchanged but quality improved substantially, with strong gains in agentic coding, multimodal reasoning, and long-horizon tool use. Community reactions claim it nearly matches Opus 4.5 and could run locally on a high-end iPad.
Related event: PrismML's Ternary Bonsai 2 27B Shrinks to 5.9GB, Retains 98.2% Performance(20 posts)→
More from Infra
- SemiAnalysis: Why GLM-5.3 Sparse Attention Doesn't Cut HBM Memory Capacity Needs — burny_tech · 2026-09-29
- Exploit Summit Montreal recap: Gamma tokens, iota SDK, $12M run rate for Targon — markjeffrey · 2026-09-29
- Bain says AI must earn $6T a year by 2031 — matching all global IT spending today — sanjaykalra · 2026-09-29
- On DGX Spark, bf16 beats int8 convrot: H3 video gen 272s vs 287s in real tests — dtdisapointingresult · 2026-09-29
- BAAI's CoWA attention cuts training latency 7.4x while matching FullAttn quality to 32B — BAAI · 2026-09-29
- BAAI's MALA attention allocates its own compute, cutting 128K training latency 2.2x — BAAI · 2026-09-29