Apple · Alibaba · TechCrunch AI
On Thursday, PrismML launched Bonsai 2 27B, its latest in a family of models, which compresses Qwen3.8 27B
Compiled by KHAO Editorial — aggregated from 1 source. See llms.txt for citation guidance.
◌ Single Source
It’s a 9x to 10x reduction in memory versus the original.
Key facts
- On Thursday, PrismML released Bonsai 2 27B, its latest in a family of models, which compresses Qwen3.8 27B, a widely used open source model from Alibaba, down to 5.9 GB
- PrismML’s approach, called “ternary” weights, simplifies that down to three: +1, −1, or 0
- It’s a 9x to 10x reduction in memory versus the original
- If AI lab PrismML isn’t on your radar yet, it should be, not because it’s raised gobs of money (it hasn’t yet, a $22.25 million seed round), but because of the technical minds involved
Summary
If AI lab PrismML isn’t on your radar yet, it should be, not because it’s raised gobs of money (it hasn’t yet, a $22.25 million seed round), but because of the technical minds involved and the potentially industry-changing tech it’s developing. PrismML is betting that capable, high-performing, reasoning large language models don’t, in fact, have to be large. It is making reasoning models so small they can fit on PCs and smartphones. (It’s even rumored to be in talks with Apple, though CEO Babak Hassibi declined to comment on that to TechCrunch.) On Thursday, PrismML released Bonsai 2 27B, its latest in a family of models, which compresses Qwen3.8 27B, a widely used open source model from Alibaba, down to 5.9 GB. PrismML was founded by a group of Caltech researchers and is led by Hassibi, a Caltech professor and an expert in compression technologies.