PrismML releases Ternary Bonsai 2 27B
A 5.9 GB ternary-weight Qwen3.8 27B that keeps 98% of its performance
Confirmed
The takeaway
On Sept 17, 2026 PrismML released Ternary Bonsai 2 27B under Apache 2.0.
Status
- Claim
Confirmed
- Our reporting
- High confidence
- Importance
- 2 of 5
- Last verified
- 1 October 2026
Your AI and this story
- GPT-6.2 Astra109 days after its cutoff
- Claude Opus 5.579 days after its cutoff
- Gemini 4 Hydrogen170 days after its cutoff
- Grok 4.7109 days after its cutoff
None of these four assistants can know about it. The closest, Claude Opus 5.5, stops 79 days before it.
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.
Sources
3 sources from 3 sites. Numbers match the chips in the text.
3 sources: 2 primary, 1 press
Primary
- PrismML: Introducing Bonsai 2 27Bprismml.com, official
- Hugging Face: prism-ml Bonsai 2 collectionhuggingface.co, code
Press
- MarkTechPost: PrismML releases Ternary Bonsai 2 27Bmarktechpost.com, press
Changes
- Filed (missed pre-window item)