Guides
Which open-weight AI models run on which hardware, what's inside them, and how to pick one: guides built on the site's own measurements.
- The best local LLMs in 2026, by what fits your GPUThe best local LLMs for every graphics card from 8 GB to 32 GB, measured from the weight files: which models fit, which file to download, and how much quality each tier keeps.
- The most downloaded AI models that fit on your GPUThe AI models people actually download, and which of them fit an RTX 5090, 4090, 3090 or 5080 — with the exact file each card can run and how much context is left over.
- The largest AI models that fit on your GPUHow big a model an RTX 5090, 4090, 3090 or 5080 can actually hold — and why the answer is the same 35B model at four different levels of compression.
- The largest open-weight AI models, by parameter countThe biggest AI models anyone can download, ranked by total parameters, with their size on disk and how many parameters each uses per token. Updated automatically as new models come out.
- Best AI models for an 8 GB GPU (RTX 4060, RTX 5060)Which open-weight LLMs actually run on an 8 GB graphics card, which file to download, and how much context is left. Updated automatically as new models come out.
- Best AI models for a Mac with 64 GB of memoryWhich open-weight LLMs run on an Apple Silicon Mac with 64 GB, which file to use, and how much context fits. Updated automatically as new models come out.
- Best AI models for a 24 GB GPU (RTX 4090, RTX 3090)Every open-weight LLM that runs on a 24 GB graphics card, with the file to download and how much context fits next to it. Updated automatically as new models come out.