← The Polylog AI Intelligence Brief
Morning Edition · Monday, September 21, 2026Published at 2:21 AM EDT · New York
PrismML Compresses a 27-Billion-Parameter Model to Ternary Weights and Keeps 98.2 Percent of Its Scores
Bonsai 2 27B stores nearly every weight as minus one, zero or plus one, shrinking a roughly 54-gigabyte model to under nine gigabytes under an Apache 2.0 licence.
PrismML, an American startup founded by a team out of Caltech, has released Bonsai 2 27B, a ternary-quantized version of Qwen3.8-27B. Nearly every weight is stored as one of three values, minus one, zero or plus one, which is about 1.585 bi…
Continue the AI Intelligence Brief
Track frontier labs, chips, export controls, model releases, regulation, and AI infrastructure.
- 5 AI intelligence signals a day
- Frontier labs, compute, and chips
- Model releases and AI infrastructure
- Source-grounded analysis with confidence labels
The Global Intelligence Brief stays free.
Part of a tracked trend
AI Inference Shifts to Consumer Devices
Over the next 3-6 months, smaller efficient architectures and inference-cost optimizations push capable AI off the cloud and onto laptops, phones, and mobile NPUs.
Townsquare
Start a discussion in Townsquare.
More from this edition
- Google Confirms Gemini Broke Out of a Security Test and Accessed Three Real Companies
- StepFun Releases Step 5 Preview, a 600-Billion-Parameter Sparse Model With Weights Due October 15
- Samsung Plans to More Than Double Output of HBM4 and HBM4E Memory Next Year
- Trump Says He Will Create an "AI Force" and Appoint an AI Czar
- Anthropic Publishes Three Scenarios for the 2030 Economy, Including One With 11.9 Percent Unemployment
- Mathematicians Split Over OpenAI's Claimed Navier-Stokes Result as Villani Calls It a Cataclysm
- Goldman Sachs Raises Its 2035 Humanoid Robot Forecast Nearly Fivefold to 6.5 Million Units
Comments
0No comments yet.