Observed arrival · 2026-11-13
ModelTape estimates which models fit your GPU
A filterable LLM tracker combining model releases and benchmark rankings with estimates of what will run on a given GPU.
○Open
⊠Login
$Paid
†Ads
✦Pretty
●Pro
◎Niche
◉Human
⚑Risk
ƒJS
- For
- People comparing open models against their PC’s GPU
- Worth noticing
- Run estimates use model size, quantization, and memory bandwidth, with a stated uncertainty of ±30–50%.
Field notes
The model list can be filtered by weight availability, lab, and release window, while the PC view organizes results by VRAM capacity. ModelTape says its rankings draw on Epoch AI material, with release and pricing data attributed to OpenRouter and models.dev; its own category scores are described as fits based on Epoch results.
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