Apple's A20 Pro features a dual-16-core Neural Engine that enables iPhones to run large AI models on-device. An iPhone 18 Pro demonstrated running a 27B parameter Bonsai model at double the speed of the iPhone 17 Pro, though memory constraints limit support for newer, denser models requiring higher bit quantization.
A 27B vision model was tasked with building canvas animations from design briefs provided as single PNG images. Six quantized versions of Qwen3.8-27B and two Bonsai variants were evaluated across three design cards using 17 objective checks per page, with results showing Opti performing competitively with Q4_K_M despite 28% smaller file size, while Bonsai struggled with JavaScript errors and token budget exhaustion.
Bonsai 2 27B is a compressed 27B-parameter multimodal model based on Qwen3.8 that achieves 9x size reduction to 5.9GB using ternary weights while retaining 98.2% of full-precision performance. The model supports 262K-token context windows and delivers high throughput and energy efficiency for local deployment across reasoning, coding, vision, and agentic tasks.