Geek Lite on Twitter / X

Ollama is now powered by MLX on Apple Silicon in preview· Ollama Blog

Today, we're previewing the fastest way to run Ollama on Apple silicon, powered by MLX, Apple's machine learning framework.

Rohan Paul on Twitter / X

👨‍🔧 Github: Native, Apple Silicon–only local LLM server. Similar to Ollama, but built on Apple's MLX- OpenAI API compatible, - Ollama‑compatible- OpenAI‑style tools + tool_choice, with tool_calls parsing and streaming deltasgithub. com/dinoki-ai/osaurus pic.twitter.com/G0NbWnEJcQ— Rohan Paul (@rohanpaul_ai) September 3, 2025

themartiano/try-omarchy

Try Omarchy on Apple Silicon without any setup.

apple-silicon-llm-bench/results/complete_results.html at main · AlexHiesch/apple-silicon-llm-bench

Systematic LLM inference benchmark for Apple Silicon: 8 backends, 7 models, 791 measurements - AlexHiesch/apple-silicon-llm-bench

Silicon Jungle on Twitter / X

i’m glad they’re doing what they’re doing.but they have one thing wrong.this should be happening at the OS level, not the browser. https://t.co/GiSLenJ0bg— Silicon Jungle (@JungleSilicon) December 2, 2024

mzau/broke-cluster

A Poor Man's Apple Silicon LLM Cluster — tuned for MLX, scalable without shame.

Cua on Twitter / X

1/ Today, as part of our broader research into Apple Silicon virtualization, we're releasing a process-scoped Metal capability layer for macOS VMs. On one M1 Ultra, prompt / generation:TinyLlama: 11.08× / 16.36×Gemma 4 12B: 7.20× / 14.54×Muse Glimmer 30B: 7.55× / 8.87× pic.twitter.com/6UwxgoDowT— Cua (@trycua) August 11, 2026

vllm-project/vllm-metal

Community maintained hardware plugin for vLLM on Apple Silicon

How Apple Can Own I/O to Own the Universe

Plus! The Great Inflation; Two-Way API Businesses; Zoom and Cities; From ETrade to eToro; Hardware-as-a-Service

Part 4: Brief history of Apple ML Stack

By Mirai Labs, frontier on-device AI lab. Building the models, inference runtime, and quantization stack from the device constraint up.

Protected by its moat, Apple has time to get AI right

Best of all, the hardware it sells today will run whatever Apple comes up with.

用Macbook微调Qwen3！手把手教你用微调给Qwen起一个新名字

clandestine.eth 🦇🔊 on Twitter / X

Heterogeneous acceleration on Apple Silicon achieved.ANE + GPU running in parallel.Mirror SD with DFlash, ported to MLX — targeting ANE + GPU simultaneously.The M-series was designed for this. We just hadn't unlocked it yet. pic.twitter.com/raSH0CMN4V— clandestine.eth 🦇🔊 (@0xClandestine) April 15, 2026

Latest News - Apple Developer

Learn about the latest technologies, events, and policies for developers.

0xSero/reap-mlx

REAP expert pruning for MoE LLMs on Apple Silicon via MLX