huggingface-local-models
huggingface1.7k installs
Find a model that fits and run it locally.
What it does
Finds compatible local models, selects a suitable quantization, and launches them with llama.cpp.
When to use it
Use when selecting models for local inference on CPU, Mac Metal, CUDA, or ROCm.
How to use it
Give it a request to run a model locally; it finds compatible models, chooses a quantization, and launches local inference.
Uses
Latest review
What you need · 2
Requires llama.cpp binaries to launch the selected model through llama-cli or llama-server.
Authenticated Hugging Face access enables use of gated repositories.
Access · 1
This skill
Hugging Face
Read
Reads Hugging Face model listings