Grok Bot template · Generative AI and LLMs
Huggingface Local Models
Select and run GGUF models locally with llama.cpp on CPU, Metal, CUDA, or ROCm.
What it can do
The skills built into this template. Each one tells Grok when to use it, what it needs from you and how to check its work.
- Search Hugging Face Hub for GGUF models
- Confirm exact GGUF filenames
- Run a model directly from the Hub
- Convert Transformers weights to GGUF
- Smoke test a local server
- Select the right quant
Apps it works with
Connect these in Grok for the best results. It also works without them: you paste the information in.
huggingface
The full template
For members
The complete Huggingface Local Models template: its identity, every skill step by step, its limits and its first-run questions, ready to paste into a new Grok Bot. Members get it, and every other template here.