Agent skill · practicalswan
huggingface-local-models
Use to select models to run locally with llama.cpp and GGUF on CPU, Mac Metal, CUDA, or ROCm. Covers finding GGUFs, quant selection, running servers, exact GGUF file lookup, conversion, and OpenAI-compatible local serving.
What it needs
About 3k tokens when loaded.
What this skill does
Hugging Face Local Models Search the Hugging Face Hub for llama.cpp-compatible GGUF repos, choose the right quant, and launch the model with llama-cli or llama-server. Default Workflow 1. Search the Hub with apps=llama.cpp. 2. Open https://huggingface.co/<repo>?local-app=llama.cpp. 3. Prefer the exact HF local-app snippet and quant recommendation when it is visible. 4. Confirm exact .gguf filenames with https://huggingface.co/api/models/<repo>/tree/main?recursive=true. 5. Launch with llama-cli -hf <repo>:<QUANT> or llama-server -hf <repo>:<QUANT>. 6. Fall back to --hf-repo plus --hf-file when the repo uses custom file naming. 7. Convert from Transformers weights only if the repo does not already expose GGUF files. Quick Start Install llama.cpp Authenticate for gated repos Search the Hub Run directly from the Hub Run an exact GGUF file Convert only when no GGUF is available Smoke test a local server Quant Choice Prefer the exact quant that HF marks as compatible on the ?local-app=llama.cpp page. Keep repo-native labels such as UD-Q4KM instead of normalizing them. Default to Q4KM unless the repo page or hardware profile suggests otherwise. Prefer Q5KM or Q6K for code or technical workloads when memory allows. Consider Q3KM, Q4KS, or repo-specific IQ / UD- variants for tighter RAM or VRAM budgets. Treat mmproj-.gguf files as projector weights, not the main checkpoint. Load References Read hub-discovery.md for URL-first workflows, model search, tree API extraction, and command reconstruction. Read quantization.md for format tables, model scaling, quality tradeoffs, and imatrix. Read hardware.md for Metal, CUDA, ROCm, or CPU build and acceleration details. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills practicalswan/huggingface-local-models