Skip to content
Hands-on AI Lab
Local AI Hardware Tools Benchmarks
  1. Home
  2. Hardware
  • Local AI
    • Video
    • LLM
    • Image
    • Model Watch
  • Hardware
    • GPU
    • Apple Silicon
    • Storage & RAM
  • Tools
    • Compatibility DB

Hardware

The machines underneath the measurements, and what changes when you swap one part of them.

No articles here yet

In this section

GPU

What a given card can and cannot run. VRAM ceilings, driver versions that move them, and the point where more memory stops helping.

Apple Silicon

Unified memory against dedicated VRAM, measured with the model, the quantization and the context length held fixed across both machines.

Storage & RAM

The parts that decide how long a model takes to load and whether offloading is survivable. Tagged storage or ram.

Everything in this section

Nothing published here yet. This page stays out of the index until an article lands in it.

Hands-on AI Lab

Local AI models run on hardware anyone can buy, with the test environment, the failed configurations, and the verification date attached to every number.

Workflow files and raw experiment data on GitHub

Local AI

  • Video
  • LLM
  • Image
  • Model Watch

Hardware

  • GPU
  • Apple Silicon
  • Storage & RAM

Tools

  • Compatibility DB
  • Benchmarks
  • RSS

Policies

  • About
  • Editorial Policy
  • AI Policy
  • Methodology

More policies

  • Corrections
  • Privacy
  • Affiliate Disclosure
  • Contact

Measurements describe the exact hardware, driver and runtime versions listed with them. Results on other configurations will differ. Nothing here is published without a human review of the final text. See the AI policy and the methodology. © 2026 Hands-on AI Lab.