What it does
modelread is an MCP server that answers whether a Hugging Face model will run on the user's hardware. According to the publisher, it reports whether the model fits, which quantization works best, an expected tokens-per-second range, and a launch command.
It suits developers who want to check a local model's hardware requirements before downloading or launching it.
The publisher's documentation is limited to a one-line description, so setup steps and runtime requirements are not documented here.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 18 Nov 2026 · last seen 18 Nov 2026 · its page on the source
modelread
Will this Hugging Face model run on my hardware? Fit, best quant, tok/s range, launch command.
v0.3.0As shown on registry.modelcontextprotocol.io when we last read it