Storia in 3 fonti

PrismML compresses 27B-parameter AI model to run on iPhone, raising questions about the future of cloud AI

PrismML compressed Alibaba's 27B-parameter Qwen 3.6 model from 54 GB to under 4 GB to run on iPhone, backed by $16.25M from Khosla Ventures.

Raccontata da

Confronto fonti

3 prospettive sulla stessa storia

AI · summaries

cryptobriefing.comStai leggendo29 g fa

PrismML compressed Alibaba's 27B-parameter Qwen 3.6 model from 54 GB to under 4 GB to run on iPhone, backed by $16.25M from Khosla Ventures.

The Information reports that Apple may be interested in PrismML’s technology. The firm is focused on shrinking AI models that...