Observed arrival · 2026-11-01
RunLLMLocal: Can My PC Run This LLM?
A browser-based checker estimates which open AI models fit a selected GPU or Mac, which quantization to use, and how fast they might run.
○Open
⊠Login
$Paid
†Ads
✦Pretty
●Pro
◎Niche
◉Human
⚑Risk
ƒJS
- For
- People choosing local AI models for their GPU or Mac
- Worth noticing
- The page says its speed estimates derive from memory bandwidth and active parameters, with a stated margin of about ±30%.
Field notes
The checker sizes weights at the selected quantization plus 10% runtime overhead and a context-length-dependent KV cache. Its stated usable-memory assumptions are 90% of VRAM and 72% for Apple Silicon; it also distinguishes fits from CPU offload, which the FAQ says can fall to 1–5 tokens per second in the described scenarios. These are estimates, not benchmark guarantees.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
○OpenPublic substance visible
✦PrettyNotable craft visible
●ProPolished or operationally mature
◎NicheUnusually specific use
One card from the complete issue