{"version":1,"type":"story","url":"https://digestai.news/story/prismml-hopes-its-tiny-llm-will-change-how-we-all-use-ai","json":"https://digestai.news/story/prismml-hopes-its-tiny-llm-will-change-how-we-all-use-ai.json","markdown":"https://digestai.news/story/prismml-hopes-its-tiny-llm-will-change-how-we-all-use-ai.md","slug":"prismml-hopes-its-tiny-llm-will-change-how-we-all-use-ai","headline":"PrismML hopes its tiny LLM will change how we all use AI","summary":"PrismML hopes its tiny LLM will change how we all use AI\nIf AI lab PrismML isn't on your radar yet, it should be. 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, just 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.)\n\nOn 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.","keyPoints":[],"whyItMatters":null,"category":{"slug":"models","name":"Generative AI & Models","url":"https://digestai.news/category/models"},"entities":{"companies":["PrismML","Khosla Ventures","Cerberus Capital","Caltech","Apple","Alibaba"],"models":["Bonsai 2 27B","Qwen3.8 27B"],"people":["Babak Hassibi","Ion Stoica"]},"firstPublishedAt":"2026-09-17T22:34:09Z","updatedAt":"2026-09-18T18:06:36Z","sourceCount":2,"hasPrimarySource":false,"sources":[{"outlet":"TechCrunch AI","title":"PrismML hopes its tiny LLM will change how we all use AI","url":"https://techcrunch.com/2026/09/17/prismml-hopes-its-tiny-llm-could-change-how-we-all-use-ai","publishedAt":"2026-09-17T22:34:09Z","type":"press","primary":false,"lead":true},{"outlet":"MarkTechPost","title":"PrismML Releases Ternary Bonsai 2 27B: A 5.9 GB Apache 2.0 Model Retaining 98.2% of Qwen3.8 27B Performance","url":"https://marktechpost.com/2026/09/18/prismml-releases-ternary-bonsai-2-27b-a-5-9-gb-apache-2-0-model-retaining-98-2-of-qwen3-8-27b-performance","publishedAt":"2026-09-18T18:06:36Z","type":"press","primary":false,"lead":false}],"sourceNotes":null,"discussions":[],"thread":{"title":"PrismML Pushes Tiny AI Into Smart Glasses","url":"https://digestai.news/thread/prismml-hopes-its-tiny-llm-will-change-how-we-all-use-ai","storyCount":2},"cite":{"text":"Digest AI, \"PrismML hopes its tiny LLM will change how we all use AI\", 17 September 2026, https://digestai.news/story/prismml-hopes-its-tiny-llm-will-change-how-we-all-use-ai","publisher":"Digest AI","title":"PrismML hopes its tiny LLM will change how we all use AI","datePublished":"2026-09-17T22:34:09Z","url":"https://digestai.news/story/prismml-hopes-its-tiny-llm-will-change-how-we-all-use-ai"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}