--- id: "2026-09-17-prismml-ternary-bonsai-2-27b" url: "https://postcutoff.com/e/2026-09-17-prismml-ternary-bonsai-2-27b/" as_of: "2026-11-22T13:32:00+01:00" date: "2026-09-17" date_precision: day category: open-source importance: 2 confidence: high status: [Confirmed] sources: 3 editor: human editor human_review: null version: "2026-10-04" --- As of: 2026-11-22 13:32 CET. Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/ Canonical page: https://postcutoff.com/e/2026-09-17-prismml-ternary-bonsai-2-27b/ # PrismML releases Ternary Bonsai 2 27B Full title: PrismML releases Ternary Bonsai 2 27B: a 5.9 GB ternary-weight Qwen3.8 27B that keeps 98% of its performance On Sept 17, 2026 PrismML released Ternary Bonsai 2 27B under Apache 2.0. It converts Qwen3.8 27B to ternary weights (−1, 0, +1 with FP16 group scaling, 1.76 effective bits per weight), shrinking it from about 54 GB to 5.9 GB while keeping 98.2% of the original's aggregate benchmark score (83.9 vs 85.4). A 27B reasoning model with image input and 262K context can then run on a laptop or one consumer GPU. ## Key facts - Base: Qwen3.8 27B; ternary weights, 1.76 effective bits/weight; 5.9 GB (~9x smaller) - Aggregate score 83.9 vs 85.4 for full precision (98.2% retained); coding and math said to be level with the original - 262K context, text + image input, reasoning on by default with configurable effort, tool calling - Apache 2.0; weights on Hugging Face (prism-ml/bonsai-2 collection); also on OpenRouter ## What happened PrismML, a startup focused on extreme compression, released its largest ternary model, built on Alibaba's open Qwen3.8 27B. ## Why it matters Near-lossless ternary compression at 27B scale makes capable reasoning models practical on local, low-power hardware. That matters for on-device AI and for how freely open-weight capability spreads. ## Your AI and this story - GPT-6.2 Astra (training cutoff May 2026): 109 days after its cutoff - Claude Opus 5.5 (training cutoff June 2026): 79 days after its cutoff - Gemini 4 Hydrogen (training cutoff March 2026): 170 days after its cutoff - Grok 4.7 (training cutoff May 2026): 109 days after its cutoff ## Sources 1. [PrismML: Introducing Bonsai 2 27B](https://prismml.com/news/bonsai-2-27b) (prismml.com, official) 2. [Hugging Face: prism-ml Bonsai 2 collection](https://huggingface.co/collections/prism-ml/bonsai-2) (huggingface.co, code) 3. [MarkTechPost: PrismML releases Ternary Bonsai 2 27B](https://www.marktechpost.com/2026/09/18/prismml-releases-ternary-bonsai-2-27b-a-5-9-gb-apache-2-0-model-retaining-98-2-of-qwen3-8-27b-performance/) (marktechpost.com, press) ## Changes - 2026-10-01 (filed): Created (missed pre-window item) ## Related - 2026-08-03: [Alibaba launches Qwen3.8-Max and open-sources the Qwen3.8 family](https://postcutoff.com/e/2026-08-03-alibaba-qwen3-8-max/index.md)