March 7, 2026

Qwen 3.5 2B outperforms larger models on iPhone 17 Pro

Qwen 3.5 2B outperforms larger models on iPhone 17 Pro

Qwen 3.5, a two-billion parameter AI model optimized with Apple’s MLX framework, has demonstrated significant advancements in on-device AI by running efficiently on the iPhone 17 Pro. This model, utilizing 6-bit quantization, showcases strong visual intelligence and outperforms larger models, making powerful AI more accessible on mobile devices. The development reflects a broader trend in mobile AI, enabling sophisticated language models to operate directly on smartphones and opening opportunities for innovative new products.

Source

Previous Article

PBOC sets USD/CNY midpoint at 6.9088, down 148 pips

Next Article

Solana integrates ERC-8004 to enhance AI agent identity and trust

You might be interested in …

Spark goes open source tomorrow

Spark goes open source tomorrow

Spark, a self-evolving intelligence, is set to become open source tomorrow, allowing developers to leverage its capabilities in a community-driven manner. This decision aligns with a broader trend in the AI sector where developers are […]