Tag: #apple-silicon

한국어English日本語中文

← All posts

• How a 26B Model Runs in 2GB of RAM — Resident Memory and Working Set Are Not the Same Number

  TurboFieldfare, posted to Show HN on July 29, 2026, claims to run Gemma 4 26B-A4B on M-series Macs in about 2GB of RAM. 14.3GB is installed on disk, the only thing resident in RAM is a 1.35GB shared core, and the expert

  2026-07-31 · 12 min read #ai#llm#quantization#apple-silicon#moe

• Why the Mac mini Became an On-Device AI Machine — What Apple's Silicon Exec Said, and What He Left Out

  Apple Silicon senior product manager Doug Brooks talked to The Deep View about demand for the Mac mini and Mac Studio and where on-device AI is heading. Why developers and small teams reach for this little desktop as a l

  2026-07-11 · 6 min read #apple-silicon#on-device-ai#local-llm#mac-mini#inference

• A Deep Dive into apple/container — The Lightweight VM Approach to macOS Containers

  We examine the limits of Docker Desktop and its single shared Linux VM on macOS, then analyze the one-VM-per-container model adopted by apple/container. The post covers the Container Machine feature unveiled at WWDC26, a

  2026-06-12 · 19 min read #apple-container#virtualization#macos#docker#container

• MLX Deep Dive — Apple's ML Framework for Apple Silicon: Unified Memory, Lazy Graphs, and the Mac-Native Flow (2026 Hands-On)

  MLX is the array framework that Apple's ML team — the same people who previously built PyTorch and JAX — rewrote from scratch for Apple Silicon. The core thesis is one sentence: the M-series GPU shares RAM with the CPU,

  2026-05-14 · 19 min read #mlx#apple-silicon#ml-framework#unified-memory#metal

• Modern Computer Architecture — CPU Pipelines, Out-of-Order, Caches, Branch Prediction, Meltdown, Apple Silicon, ARM, RISC-V, SIMD, GPU Deep Dive (2025)

  Why arrays beat linked lists, why a branch can be 10x slower, how M1 beat Intel. CPU pipelines, Out-of-Order, L1 to L3 caches, branch prediction, Meltdown/Spectre, Apple Silicon, ARM/x86/RISC-V, SIMD, GPU SM/Warp, HBM/CX

  2026-04-15 · 15 min read #computer-architecture#cpu#cache#branch-prediction#apple-silicon

• Running LLMs on Apple Silicon: Inside M4/M5 Architecture for AI Inference

  A deep technical dive into Apple M4/M5 Unified Memory Architecture and its implications for LLM inference. Covers the Neural Engine, MLX framework, llama.cpp Metal backend, real benchmarks, and an honest comparison with

  2026-03-18 · 14 min read #apple-silicon#m5#model-serving#unified-memory#mlx