Observed arrival · 2026-11-20
modelread asks whether an LLM fits your machine
A hardware-fit checker for Hugging Face models that estimates speed, suggests a fitting quantization, and provides launch commands.
○Open
⊠Login
$Paid
†Ads
✦Pretty
●Pro
◎Niche
◉Human
⚑Risk
ƒJS
- For
- Local LLM users and coding-agent operators
- Worth noticing
- It distinguishes measured, calibrated, and uncalibrated speed ranges, and exposes MCP tools for fit, discovery, and hardware comparison.
Field notes
Users can search for a Hugging Face repository or describe a task, then compare fit against a selected device. The page says it reads repository file sizes and tensor headers, accounts for architecture-specific KV cache, and labels speed figures by whether they are measured, calibrated, or uncalibrated estimates. Its MCP surface lists fit estimation, model discovery, and comparison across as many as eight devices.
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
ƒJavaScriptBrowser-side code central
One card from the complete issue