DEV-TOOLSMarch 23, 20261 min read11 views

iPhone 17 Pro Demonstrated Running a 400B LLM

Recent demonstrations show the iPhone 17 Pro successfully running a 400-billion parameter Large Language Model (LLM) on-device, highlighting a massive leap in mobile processing power.

JavaScript is not available. We’ve detected that JavaScript is disabled in this browser. Please enable JavaScript or switch to a supported browser to continue using x.com. You can see a list of supported browsers in our Help Center. Help Center Terms of Service Privacy Policy Cookie Policy Imprint Ads info © 2026 X Corp.

Source: Hacker News

More in this category

dev-tools

HomeLab #1: MikroTik as a Home Router

A comprehensive guide on setting up a MikroTik router for a home lab, covering ISP configurations, PPPoE, MAC cloning, and PoE access point setup.

dev-tools

Bananas sprout in Rayleigh Garden UK after 15 years

Rising temperatures due to climate change are transforming British gardens, allowing tropical plants like bananas to flower and fruit. After 15 years, a couple in Essex was astonished to see their banana plants finally bear fruit following a recent heatwave.

dev-tools

The death and rebirth of my home server

A sudden power outage delivered the final blow to a long-running Raspberry Pi home server's microSD card. This article details the process of rebuilding the server using NixOS, minimizing disk writes, and repurposing old HDDs into a Btrfs RAID1 pool.

dev-tools

What I learned selling 2,500 MIDI recorders: Hardware is not so hard

A software engineer shares his journey of launching Jamcorder and selling 2,500 units, debunking the myth that hardware is inherently difficult and offering practical tips for hardware startups.

dev-tools

Token Plan Upgraded: Individual Plan Launched, Team Plan More Affordable with Qwen 3.8 Max Preview

Token Plan has upgraded its offerings, introducing a new Individual plan and lowering prices for the Team plan. Users can now access advanced models like Qwen 3.8 Max Preview with unified access to text, vision, speech, and image generation.

dev-tools

Qwen3.8 is launching and going open-weight soon

Alibaba is set to launch Qwen3.8, a massive 2.4-trillion-parameter AI model that will soon be open-weight. A preview version, Qwen3.8-Max-Preview, is already available for early testing on Alibaba's platforms.