Observed arrival · 2026-10-18
RigRunsAI’s local-model fit calculator
A calculator estimates which local language models fit a given GPU or unified-memory machine, with quantization and context length included.
○Open
⊠Login
$Paid
†Ads
✦Pretty
●Pro
◎Niche
◉Human
⚑Risk
ƒJS
- For
- PC owners checking local-model fit
- Worth noticing
- The calculator separates model weights, KV-cache use, and overhead, then labels results Fits, Tight, Offload, or No.
Field notes
The preset list spans discrete GPUs, Apple silicon memory configurations, and handhelds, while custom inputs include memory type, system RAM, and bandwidth. Users can compare models across quantization levels and context sizes; the RTX 4070 reference table also shows Ollama commands alongside fit verdicts and estimated speed ranges. The extracted material does not show the calculation methodology.
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