{"schema":"postcutoff/event@1","as_of":"2026-11-22T13:32:00+01:00","url":"https://postcutoff.com/e/2026-09-17-prismml-ternary-bonsai-2-27b/","md":"https://postcutoff.com/e/2026-09-17-prismml-ternary-bonsai-2-27b/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"2026-09-17-prismml-ternary-bonsai-2-27b","date":"2026-09-17","date_precision":"day","short_title":"PrismML releases Ternary Bonsai 2 27B","deck":"A 5.9 GB ternary-weight Qwen3.8 27B that keeps 98% of its performance","takeaway":"On Sept 17, 2026 PrismML released Ternary Bonsai 2 27B under Apache 2.0.","category":"open-source","category_label":"Open source","importance":2,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":[{"n":1,"title":"PrismML: Introducing Bonsai 2 27B","url":"https://prismml.com/news/bonsai-2-27b","type":"official","group":"primary","domain":"prismml.com"},{"n":2,"title":"Hugging Face: prism-ml Bonsai 2 collection","url":"https://huggingface.co/collections/prism-ml/bonsai-2","type":"code","group":"primary","domain":"huggingface.co"},{"n":3,"title":"MarkTechPost: PrismML releases Ternary Bonsai 2 27B","url":"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/","type":"press","group":"press","domain":"marktechpost.com"}],"official":2,"filed":"2026-10-01","updated":"2026-10-01","orgs":["PrismML"],"title":"PrismML releases Ternary Bonsai 2 27B: a 5.9 GB ternary-weight Qwen3.8 27B that keeps 98% of its performance","summary":"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"],"key_numbers":[],"tags":["quantization","ternary","edge-ai","open-weights","qwen","efficiency"],"science":null,"body_md":"## What happened\n\nPrismML, a startup focused on extreme compression, released its largest ternary model, built on Alibaba's open Qwen3.8 27B.\n\n## Why it matters\n\nNear-lossless ternary compression at 27B scale makes capable reasoning models practical on local, low-power hardware. That matters for\non-device AI and for how freely open-weight capability spreads.","disputed":[],"related":[{"id":"2026-08-03-alibaba-qwen3-8-max","url":"https://postcutoff.com/e/2026-08-03-alibaba-qwen3-8-max/","date":"2026-08-03","date_precision":"day","short_title":"Alibaba launches Qwen3.8-Max and open-sources the Qwen3.8 family","deck":null,"takeaway":"Together with Kimi K3 and DeepSeek V4, Qwen3.8 means three Chinese labs released trillion-scale open-weight models within four months.","category":"model-release","category_label":"Model releases","importance":4,"confidence":"medium","status":{"key":"partly","labels":["Partly confirmed"]},"sources":5,"official":1,"filed":"2026-09-29","updated":"2026-09-29","orgs":["Alibaba","Qwen"]}],"people":[],"posts":[],"videos":[],"models":[],"changes":[{"date":"2026-10-01","type":"filed","text":"Created (missed pre-window item)"}],"provenance":{"agents":[{"model":"Claude Opus 5.5","maker":"Anthropic","tool":"Claude Code"}],"filed":"2026-10-01","run":null,"sources_read":null,"updated":"2026-10-01","human_review":null,"version":{"date":"2026-10-04"}},"gaps":[{"model_id":"gpt-6-2-astra","name":"GPT-6.2 Astra","cutoff":"2026-05","days_after":109,"in_training_data":false},{"model_id":"claude-opus-5-5","name":"Claude Opus 5.5","cutoff":"2026-06","days_after":79,"in_training_data":false},{"model_id":"gemini-4-hydrogen","name":"Gemini 4 Hydrogen","cutoff":"2026-03","days_after":170,"in_training_data":false},{"model_id":"grok-4-7","name":"Grok 4.7","cutoff":"2026-05","days_after":109,"in_training_data":false}],"short_url":null}