---
author: "Umesh Malik"
canonical: "https://umesh-malik.com/blog/tag/apple-silicon"
description: "Explore articles tagged with Apple Silicon by Umesh Malik — AI Engineer, LLM & GenAI Developer. Learn Apple Silicon best practices, practical tips, and in-depth guides."
title: "Umesh Malik's Blog - Apple Silicon Articles | Apple Silicon Tutorials"
tokens: 306
generator: "scripts/generate-page-markdown.mjs"
---

[← Back to Blog](https://umesh-malik.com/blog)

# Apple Silicon

2 articles

 [![Dashboard-style cover showing Kimi K3's 2.8 trillion parameters streamed from four SSDs to a MacBook at 1 token per second](https://umesh-malik.com/blog/run-kimi-k3-locally-macbook-ssd-streaming-cover.png)

LLM Engineering • Sep 9, 2026

### Run Kimi K3 Locally: 2.8T Params From 4 SSDs at 1 Tok/s

Run Kimi K3 locally on a MacBook by streaming 1.45TB of experts from four SSDs — the 1 tok/s number, and why doubling drives doesn't double speed.

7 min read

Read more →](https://umesh-malik.com/blog/run-kimi-k3-locally-macbook-ssd-streaming)

 [![How a paravirtualized Metal device reporting Apple GPU family 5 makes llama.cpp disable its simdgroup matrix kernels, and the throughput that returns when the guest reports family 9](https://umesh-malik.com/blog/fix-slow-llm-inference-macos-vms-cover.png)

LLM Engineering • Aug 11, 2026

### Fix slow LLM inference in macOS VMs: 12.6 → 207 tok/s

LLM inference in macOS VMs collapses to 12.63 tok/s because the guest reports GPU family 5 and llama.cpp drops its matrix kernels. The check, and its limits.

9 min read

Read more →](https://umesh-malik.com/blog/fix-slow-llm-inference-macos-vms)
