The new iPad mini(apple.com)
49 points by soheilpro | 19 comments
Apple press release announcing a redesigned iPad mini with an 8.5-inch OLED display, A20 Pro chip, IP67 rating, N1 and C2 chips, and iPadOS 27.
#apple-silicon on Hacker News
85 stories tagged apple-silicon, newest first.
Show HN: OnKey – I'm a bad singer, so I built an app to show where I'm off-key(github.com)
210 points by dsmurrell | 89 comments
GitHub repository for OnKey, a free open-source Mac singing trainer that learns songs played in Spotify, Apple Music, or YouTube and scores your pitch.
Android apps running native on macOS(github.com)
307 points by flocked | 164 comments
GitHub repository for Mac.apk, an AGPL-3.0 open-source project that runs Android apps natively on Apple Silicon Macs.
Show HN: Which Mac runs which LLM, and how fast(macyou.co)
5 points by bagdaerdev | 2 comments
A web calculator that estimates which large language models can run on various Mac models and how fast they generate tokens.
Show HN: I got tired of btop not seeing my Mac's chip, so I built siltop(github.com)
12 points by cloaky233 | 14 comments
GitHub repository for siltop, a Rust terminal system monitor for Apple Silicon Macs showing power, GPU, per-core clocks and temperatures without sudo.
Show HN: Pulse Local, a Mac budgeting app whose AI models run on your machine(pulseos.finance)
102 points by niztk | 55 comments
Landing page for Pulse Local, a free Mac budgeting app that answers spending questions using small AI models running entirely on the user's machine.
A Dynamic and Distributed Virtual GPU Cloud Built on Idle Apple Silicon Devices(machinelearning.apple.com)
239 points by acossta | 96 comments
Apple Machine Learning Research paper page for Minions, a distributed virtual GPU cloud that uses idle Apple Silicon devices for ML inference.
We turned EmbeddingGemma 2 into a speech-to-text model(eg2.haku.sh)
404 points by amrrs | 86 comments
Landing page for Embedding Gemma Transcribe, a free macOS app that adapts Google's EmbeddingGemma 2 into an on-device speech-to-text model.
Show HN: Rgpu – a PyTorch device whose tensors live on a remote GPU(github.com)
46 points by boxstream | 2 comments
GitHub repository for rgpu, a PyTorch device that runs tensor operations on a remote NVIDIA GPU while Python code stays on the local machine, including Macs.
The Forgetful CPU (Linux on M4)(yuka.dev)
249 points by signa11 | 168 comments
A blog post detailing how the author first booted Linux on an Apple M4 Mac mini, building on Asahi Linux work.
Running local LLMs on your Mac: what fits, what's free, and what's overkill(typetab.app)
8 points by donk8r | 2 comments
A TypeTab blog post explaining which local LLM model sizes fit on Apple Silicon Macs, which free tools to use, and practical everyday uses.
Pentium II at 600Mhz with Voodoo 3 Emulated on 86Box with M6 Mac Mini(nyaa.sh)
263 points by hugh4life | 114 comments
A blog review of running cycle-accurate retro PC emulation in 86Box on an M6 Mac Mini, reaching an emulated 600MHz Pentium II with Voodoo 3.
Building a Linux GPU Driver for the M4 Mac Mini in One Month(codyho.dev)
386 points by ADevWithAnIdea | 233 comments
Blog post by Cody Ho describing building an OpenGL ES 3.0 compliant Linux GPU driver for the M4 Mac Mini and MacBook Neo in about a month using AI prompting.
Asahi Linux on M3(asahilinux.org)
513 points by mdp2021 | 313 comments
Phoronix news article reporting that Asahi Linux now officially supports Apple M3, M3 Pro, and M3 Max Macs, with some feature caveats and the M3 Ultra excluded.
Asahi Linux Progress Report: Linux 7.2(asahilinux.org)
377 points by pizzaiolo | 197 comments
Asahi Linux blog progress report covering developments in porting Linux to Apple Silicon Macs around the Linux 7.2 kernel release.
New Mac mini, featuring M6 and M5 Pro(apple.com)
526 points by runako | 326 comments
Apple Newsroom press release announcing a new Mac mini with M6 and M5 Pro chips, touting faster AI performance, graphics, storage, and connectivity.
New Mac Studio with M5 Max and M5 Ultra(apple.com)
805 points by interpol_p | 535 comments
Apple Newsroom press release announcing a new Mac Studio with M5 Max and M5 Ultra chips, up to 512GB unified memory, aimed at local AI and pro workflows.
Apple introduces M6 and M5 Ultra(apple.com)
1261 points by interpol_p | 1203 comments
Apple Newsroom press release announcing the M6 chip, Apple's first 2 nm chip, and the M5 Ultra, its first quad-die architecture.
Xiaomi: New CPU matches Apple cores single threaded, much faster multithreaded(twitter.com)
967 points by tosh | 702 comments
A post by Daniel Lemire on X discussing Xiaomi's Xring O3 CPU, its large cache, ARM C1-Ultra cores with SME2/SVE2, and performance compared to Apple chips.
H3-metal – Native MiniMax-H3 inference for Apple Silicon(github.com)
418 points by swyx | 93 comments
GitHub repository for h3.c by antirez, a native MiniMax H3 model inference engine for Mac computers using Apple Silicon/Metal.
Show HN: Open-source engine running Gemma 4 26B in 2 GB RAM on any M-series Mac(github.com)
845 points by gitpusher42 | 300 comments
GitHub repo for TurboFieldfare, a Swift/Metal inference engine running 4-bit Gemma 4 26B-A4B on M-series Macs in about 2 GB RAM by streaming experts from SSD.
Nativ: Run frontier open models locally on your Mac(blaizzy.github.io)
361 points by aratahikaru5 | 122 comments
Landing page for Nativ, an open-source macOS app for downloading and running open AI models locally on Apple Silicon without accounts or cloud.
Show HN: Davit, a Apple Containers UI(davit.app)
364 points by xinit | 93 comments
Landing page for Davit, a free, MIT-licensed native macOS app providing a UI for Apple's container platform to run Linux containers on Apple silicon.
Command and Conquer Generals natively ported to macOS, iPhone, iPad using Fable(github.com)
644 points by asronline | 269 comments
GitHub repository porting Command & Conquer Generals: Zero Hour to run natively on macOS, iPhone and iPad using the GPL source, DXVK/MoltenVK, and touch controls.
Asahi Linux 7.1 Progress Report(asahilinux.org)
507 points by pantalaimon | 182 comments
Asahi Linux blog progress report for Linux 7.1, covering M3 support progress, Apple hardware bugs, and other updates.
Running local models is good now(vickiboykis.com)
1490 points by jfb | 569 comments
Vicki Boykis blog post arguing that running LLMs locally on a 64GB M2 Mac is now practical, describing models like Mistral 7B, Gemma 3, OpenAI OSS-20B and Qwen 3.
macOS 27 Beta breaks the ability to boot Asahi Linux(phoronix.com)
358 points by josephcsible | 146 comments
Phoronix news article reporting that the macOS 27 beta changes the boot picker so Asahi Linux partitions are no longer visible or bootable on Apple Silicon Macs.
Apple Core AI Framework(developer.apple.com)
335 points by hmokiguess | 96 comments
Apple developer documentation for Core AI, a beta framework for building, running, and deploying AI models in apps on Apple silicon across CPU, GPU, and Neural Engine.
Indexing a year of video locally on a 2021 MacBook with Gemma4-31B (50GB swap)(blog.simbastack.com)
451 points by asenna | 127 comments
Blog post describing how the author used Gemma 4 running locally on a five-year-old MacBook to index a year of personal video footage overnight.
RTX 5090 and M4 MacBook Air: Can It Game?(scottjg.com)
671 points by allenleee | 159 comments
A long blog post testing whether an NVIDIA RTX 5090 external GPU connected to an M4 MacBook Air can be used for gaming, shown running Ubuntu.
MacBook Neo Deep Dive: Benchmarks, Wafer Economics, and the 8GB Gamble(jdhodges.com)
319 points by tosh | 373 comments
A personal blog post analyzing Apple's MacBook Neo, covering benchmarks, chip wafer economics, and its 8GB RAM configuration.
Running local models on an M4 with 24GB memory(jola.dev)
525 points by shintoist | 156 comments
A blog post describing a setup for running local LLMs such as Qwen via LM Studio on an Apple M4 Mac with 24GB of memory.
DeepSeek 4 Flash local inference engine for Metal(github.com)
461 points by tamnd | 133 comments
GitHub repository for ds4 by antirez, a local inference engine for running the DeepSeek 4 Flash model on Apple Metal, released under the MIT license.
Asahi Linux Progress Linux 7.0(asahilinux.org)
590 points by elisaado | 283 comments
Asahi Linux blog progress report marking the release of Linux 7.0 and updates on Linux support for Apple Silicon Macs.
Darkbloom – Private inference on idle Macs(darkbloom.dev)
461 points by twapi | 227 comments
Research preview page from Eigen Labs presenting Darkbloom, a decentralized network for private AI inference running on idle Apple Silicon Macs.
Apple's accidental moat: How the "AI Loser" may end up winning(adlrocha.substack.com)
347 points by walterbell | 302 comments
Substack essay arguing Apple, seen as an AI laggard, may win through its hardware and on-device advantage as frontier AI models become commoditized.
Apple approves driver that lets Nvidia eGPUs work with Arm Macs(twitter.com)
466 points by naves | 210 comments
Tinygrad/Tiny Corp's announcement, covered by The Verge, that Apple signed its driver letting Nvidia eGPUs work on Arm Macs without disabling SIP.
Show HN: Apfel – The free AI already on your Mac(apfel.franzai.com)
626 points by franze | 137 comments
Landing page for apfel, an MIT-licensed tool exposing Apple's built-in on-device LLM on Macs as a CLI, OpenAI-compatible server, and chat.
Ollama is now powered by MLX on Apple Silicon in preview(ollama.com)
588 points by redundantly | 303 comments
Ollama blog post announcing a preview of Ollama running on Apple's MLX framework for Apple Silicon Macs.
The MacBook Neo(daringfireball.net)
603 points by etothet | 947 comments
John Gruber's Daring Fireball piece on Apple's MacBook Neo, tracing how iPhone A-series chip performance foreshadowed it.
Nvidia PersonaPlex 7B on Apple Silicon: Full-Duplex Speech-to-Speech in Swift(blog.ivan.digital)
352 points by ipotapov | 113 comments
A Medium blog post on running NVIDIA's PersonaPlex 7B full-duplex speech-to-speech model natively in Swift on Apple Silicon using MLX.
MacBook Neo(apple.com)
1891 points by dm | 2192 comments
Apple Newsroom press release announcing the MacBook Neo, a 13-inch aluminum laptop with Apple silicon and all-day battery life starting at $599.
MacBook Air with M5(apple.com)
380 points by Garbage | 422 comments
Apple Newsroom press release announcing the MacBook Air with the M5 chip, doubled starting storage, and improved wireless connectivity.
MacBook Pro with M5 Pro and M5 Max(apple.com)
812 points by scrlk | 874 comments
Apple Newsroom press release announcing MacBook Pro models with M5 Pro and M5 Max chips, faster SSDs, and 1TB starting storage.
Inside the M4 Apple Neural Engine, Part 1: Reverse Engineering(maderix.substack.com)
359 points by zdw | 104 comments
A Substack post, the first in a series, describing how the author reverse engineered the Apple M4 Neural Engine to bypass CoreML and talk directly to the hardware.
Asahi Linux Progress Report: Linux 6.19(asahilinux.org)
347 points by mkurz | 124 comments
Asahi Linux blog post giving a progress report on Apple Silicon Linux support coinciding with the Linux 6.19 kernel release.
Fedora Asahi Remix is now working on Apple M3(bsky.app)
540 points by todsacerdoti | 201 comments
Bluesky post by Michael Reeves announcing a KDE Plasma desktop running under Fedora Asahi Remix on an Apple M3 Mac, with a photo of the working system.
OpenBSD-current now runs as guest under Apple Hypervisor(undeadly.org)
386 points by gpi | 52 comments
OpenBSD Journal article reporting that OpenBSD-current on arm64 now runs as a guest OS under Apple Hypervisor, following commits by Helg Bredow and Stefan Fritsch.
1.5 TB of VRAM on Mac Studio – RDMA over Thunderbolt 5(jeffgeerling.com)
569 points by rbanffy | 211 comments
Jeff Geerling blog post about clustering four Mac Studios with RDMA over Thunderbolt 5 to pool 1.5 TB of unified memory for AI workloads.
Boring is what we wanted(512pixels.net)
413 points by Amorymeltzer | 239 comments
A 512 Pixels blog post by Stephen Hackett reflecting on five years of Apple Silicon Macs from M1 to M5 and arguing steady, boring iteration is what users wanted.
M5 MacBook Pro(apple.com)
331 points by tambourine_man | 463 comments
Apple's MacBook Pro product page announcing the 14-inch model with the M5 chip, available for pre-order and shipping October 22.
Apple M5 chip(apple.com)
1204 points by mihau | 1307 comments
Apple press release announcing the M5 chip, with a next-generation GPU featuring per-core Neural Accelerators, a faster CPU and Neural Engine, and higher memory bandwidth.
I'm spoiled by Apple Silicon but still love Framework(simonhartcher.com)
362 points by deevus | 480 comments
Personal blog post by Simon Hartcher comparing Apple Silicon MacBooks with the Framework laptop, explaining why he prefers Apple's performance but still likes Framework.
Experimenting with Local LLMs on macOS(blog.6nok.org)
367 points by frontsideair | 241 comments
A personal blog post by a self-described LLM skeptic explaining how to download and run large language models locally on a Mac.
Ask HN: Why hasn't x86 caught up with Apple M series?
329 points by stephenheron | 434 comments
Ask HN post asking why x86 laptop chips like AMD's Ryzen AI 340 still lag Apple's M1 in battery efficiency and thermals.
MacBook Pro Insomnia(manuel.bernhardt.io)
473 points by speckx | 216 comments
A short blog post about diagnosing overnight battery drain on an M1 Max MacBook Pro using pmset logs and the Sleep Aid app.
iPhone 11 emulation done in QEMU(github.com)
360 points by 71bw | 30 comments
GitHub repository for QEMUAppleSilicon, a QEMU fork that emulates Apple Silicon devices, currently only the iPhone 11.
An appeal to Apple from Anukari(anukari.com)
347 points by humbledrone | 174 comments
A devlog post from the Anukari developer appealing to Apple's Metal team for help making the app's GPU performance reliable across Apple silicon Macs.
Triforce – a beamformer for Apple Silicon laptops(github.com)
555 points by tosh | 200 comments
Triforce is a Rust LV2 plugin implementing an MVDR adaptive beamformer for the microphone arrays in Apple Silicon MacBooks.
MacBook Air M4(apple.com)
670 points by tosh | 827 comments
Apple's official product page for the MacBook Air laptop, featuring the M4 chip model.
Apple M3 Ultra(apple.com)
1016 points by ksec | 958 comments
Apple press release announcing the M3 Ultra chip, claiming up to 2.6x M1 Ultra performance, Thunderbolt 5, and over half a terabyte of unified memory.
Resigning as Asahi Linux project lead(marcan.st)
918 points by Shank | 758 comments
Blog post by Hector Martin (marcan) announcing his resignation as project lead of Asahi Linux, recounting his homebrew history and reasons including burnout.
Asahi Linux lead developer Hector Martin resigns from Linux kernel(lkml.org)
848 points by Mond_ | 842 comments
LKML patch from Hector Martin removing himself as maintainer of ARM/Apple machine support in the Linux kernel, citing loss of faith in the kernel development process.
New speculative attacks on Apple CPUs(predictors.fail)
1020 points by cylo | 334 comments
Landing page for SLAP and FLOP, two speculative execution attacks exploiting load address and load value prediction on Apple Silicon CPUs.
M4 Mac mini's efficiency(jeffgeerling.com)
518 points by marinesebastian | 515 comments
Jeff Geerling blog post from November 2024 on the power efficiency of Apple's M4 Mac mini, written amid his Pi 5 GPU and AmpereOne server testing.
Apple's M4 Max chip is the fastest single-core performer in consumer computing(twitter.com)
341 points by retskrad | 451 comments
An X (Twitter) post claiming Apple's M4 Max chip has the fastest single-core performance among consumer computers; the post content did not load.
An Update on Apple M1/M2 GPU Drivers(lwn.net)
568 points by MrBuddyCasino | 234 comments
LWN article covering Alyssa Rosenzweig's XDC 2024 talk on the status of the Rust-based Linux GPU driver for Apple M1/M2, including conformance and gaming support.
M4 MacBook Pro(apple.com)
830 points by tosh | 1172 comments
Apple press release from October 30, 2024 announcing the new MacBook Pro with M4, M4 Pro, and M4 Max chips, a 12MP Center Stage camera, Thunderbolt 5, and a nano-texture display option.
New Mac Mini with M4(apple.com)
364 points by victorbjorklund | 544 comments
Apple press release announcing the redesigned Mac mini with M4 and M4 Pro chips, built for Apple Intelligence and billed as the first carbon neutral Mac.
New iMac with M4(apple.com)
488 points by tosh | 1024 comments
Apple press release from October 28, 2024 announcing the new iMac with the M4 chip, Apple Intelligence, nano-texture display option, 12MP camera, and new colors.
AAA Gaming on Asahi Linux(rosenzweig.io)
861 points by 6a74 | 318 comments
Blog post announcing the Asahi Linux game playing toolkit, combining Vulkan 1.3 drivers with x86 emulation and Windows compatibility to run AAA games on M1 Macs.
Virtualizing iOS on Apple Silicon(nickb.website)
333 points by walterbell | 128 comments
A blog post by Nick Botticelli, dated April 30, 2024, about virtualizing iOS on Apple Silicon Macs.
Hackintosh is almost dead(aplus.rs)
482 points by ingve | 473 comments
Blog post by Aleksandar Vacić arguing that Hackintosh, running macOS on non-Apple hardware, is nearly dead, reflecting on his builds since 2020.
New 13- and 15‑inch MacBook Air with M3 chip(apple.com)
340 points by dm | 813 comments
Apple press release from March 4, 2024 announcing the 13- and 15-inch MacBook Air with the M3 chip, faster Wi-Fi, and dual external display support.
Asahi Linux project's OpenGL support on Apple Silicon officially surpasses Apple(arstechnica.com)
324 points by throwaway2037 | 132 comments
Ars Technica article reporting that Asahi Linux's GPU driver for Apple Silicon now supports the latest OpenGL and OpenGL ES versions, surpassing Apple's own support.
Tracking developer build times to decide if the M3 MacBook is worth upgrading(incident.io)
593 points by paprikati | 378 comments
An incident.io engineering blog post analyzing collected developer build telemetry to compare M1, M2, and M3 MacBooks and decide whether upgrading is worthwhile.
Show HN: Rem: Remember Everything (open source)(github.com)
488 points by jasonjmcghee | 171 comments
GitHub repository for Rem, an open source macOS app that locally records everything you view on an Apple Silicon computer so you can search it later.
macOS Sonoma Boot Failures(github.com)
609 points by ColoursofOSINT | 252 comments
Asahi Linux wiki page explaining macOS Sonoma and Ventura 13.6 bugs that can leave dual-boot Apple Silicon Macs stuck at a black screen requiring DFU recovery.
Apple unveils M3, M3 Pro, and M3 Max(apple.com)
997 points by ehPReth | 1053 comments
Apple press release announcing the M3, M3 Pro, and M3 Max chips, its first 3-nanometer chips for personal computers, with a new GPU architecture and faster CPU and Neural Engine.
iLeakage: Browser-Based Timerless Speculative Execution Attacks on Apple Devices(ileakage.com)
565 points by aw1621107 | 196 comments
Project site for iLeakage, a research attack using timerless speculative execution in Safari to leak data on Apple devices.
Guide to running Llama 2 locally(replicate.com)
573 points by bfirsh | 153 comments
Replicate blog post explaining how to run Meta's Llama 2 model locally on M1/M2 Macs, Windows, Linux, and phones without an internet connection.
OpenGL 3.1 on Asahi Linux(asahilinux.org)
483 points by simjue | 287 comments
Asahi Linux blog post announcing its Apple Silicon GPU drivers now support OpenGL 3.1 and OpenGL ES 3.0, up from OpenGL 2.1 and ES 2.0.
Apple unveils new Mac Studio and brings Apple Silicon to Mac Pro(apple.com)
432 points by 0xedb | 357 comments
Apple press release from June 5, 2023 announcing a new Mac Studio with M2 Max/M2 Ultra and an M2 Ultra Mac Pro with PCIe expansion.
Apple Introduces M2 Ultra(apple.com)
324 points by 0xedb | 311 comments
Apple Newsroom press release from June 5, 2023 announcing the M2 Ultra chip with a faster CPU and GPU and support for more unified memory.
Apple halted M2 chip production in January amid 'plummeting' Mac sales(macrumors.com)
360 points by tosh | 800 comments
MacRumors article reporting that Apple halted M2 chip production in early 2023 amid a slump in global MacBook demand, citing a Korean report.