AnalysisAI ModelsJuly 17, 2026
Bonsai 27B runs on iPhone after 1-bit quantization
PrismML's Bonsai 27B, based on Qwen3.6-27B, uses true binary quantization to shrink from ~54GB to 3.9GB, fitting on an iPhone while retaining ~90% of benchmark performance.
1 source
Daily brief
Get tomorrow's AI brief in your inbox
More stories today
- Tool installs configurations for Claude Code, Codex CLI, Gemini CLI, and Cursor
- Baidu's Apollo Go begins robotaxi road tests in London
- OpenAI releases GPT Transcribe speech-to-text model
- SKT and KRAFTON release A.X-K2 model
- AI-2027 and AI-2040 researcher calls 'Pacing the Frontier' letter a success