PrismML compresses Alibaba's Qwen3.8 into 5.9 GB Bonsai 2 27B for PCs
Topic: technologyRegion: north americaUpdated: i2 outletsSources: 3Spectrum: Center Only⏱ 1 min read
Story Summary
SITUATION
PrismML compressed Alibaba's Qwen3.8 27B into a 5.9 GB model called Bonsai 2 27B, a 9x–10x reduction in memory that PrismML says matches 98% of Qwen's aggregate benchmark scores. PrismML says Bonsai 2 can run on PCs and possibly high-end smartphones, and the startup has raised $22.25 million in seed funding.
Coveragetap to expand ▾Spectrum: Center Only🌍US: 1 · Asia: 1
Political Spectrum
Position is inferred from coverage mix.
i2 outlets · Center
Left
Center
Right
Left: 0
Center: 2
Right: 0
Geography Coverage
Distribution of where coverage is coming from.
i2 unique outlets · Dominant: US/Canada
KEY FACTS
- The 'Ternary Bonsai 2 27B' is an AI model that reduces the size of the Qwen3.8 27B to 5.9GB while maintaining 98.2% of its performance. - GIGAZINE
- The 'Ternary Bonsai 2 27B' is an AI model that reduces the size of the Qwen3.8 27B to 5.9GB while maintaining 98.2% of its performance.
- PrismML released Bonsai 2 27B, a compressed version of Alibaba's Qwen3.8 27B reduced to 5.9 GB.
- PrismML says Bonsai 2 matches 98% of Qwen's aggregate benchmark scores.
- PrismML was founded by Caltech researchers and is led by CEO Babak Hassibi.
- Ion Stoica is listed as an adviser to PrismML.
- PrismML has raised $22.25 million in seed funding and is backed by Khosla Ventures, Cerberus Capital, and Caltech.
HISTORICAL CONTEXT
The 'Ternary Bonsai 2 27B' is an AI model that reduces the size of the Qwen3.8 27B to 5.9GB while maintaining 98.2% of its performance. - GIGAZINE The 'Ternary
Brief
PrismML released Bonsai 2 27B, a compressed version of Alibaba's Qwen3.8 27B that fits on PCs and possibly high-end smartphones by reducing the model to 5.9 GB. The company says Bonsai 2 matches 98% of Qwen's aggregate benchmark scores while it has raised $22.25 million in seed funding.
Sources
3 of 3 linked articles
The 'Ternary Bonsai 2 27B' is an AI model that reduces the size of the Qwen3.8 27B to 5.9GB while maintaining 98.2% of its performance.
gigazine.net23h agoLeft
↗
PrismML releases compressed Bonsai 2 27B model — TechCrunch
ua.newsSep 17Left
↗
PrismML hopes its tiny LLM will change how we all use AI
techcrunch.comSep 17Left
↗