Observed arrival · 2026-11-02
Run AI Local’s machine-by-machine LLM fit checker
A free fit checker estimates which open-source language models fit a Mac’s memory or a PC’s graphics card, with reference speeds and GPU rental comparisons.
○Open
⊠Login
$Paid
†Ads
✦Pretty
●Pro
◎Niche
◉Human
⚑Risk
ƒJS
- For
- Mac and PC owners comparing local LLM options
- Worth noticing
- Fit labels distinguish comfortable memory headroom, fits over 90%, low-bit-only builds, and models described as too slow to enjoy.
Field notes
The checker exposes its memory assumptions: model file plus a KV cache calculated from model configuration, with sliding-window and hybrid layers counted only up to what they retain, and roughly 1 GB for runtime buffers. Results also distinguish a fit that leaves room to spare from one using more than 90% of memory. Rental entries carry provider names, currencies, and source or check dates, making the price comparison easier to inspect.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
○OpenPublic substance visible
$PaidCommerce or pricing visible
✦PrettyNotable craft visible
●ProPolished or operationally mature
◎NicheUnusually specific use
One card from the complete issue