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.

1.25x

Quality

88%

Does it follow best practices?

Impact

73%

1.25x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Preview

This is a new way to view eval results. We're still working on it, so the layout may change.

Run	Type	Date	Status
baseline vs usage-spec With / without context 4 months ago Completed	With / without context	4 months ago	Completed

Eval run

Name: huggingface-local-models
Rating: 86.6 (1 reviews)
Author: huggingface

019e929a-cb80-76c8-8bfa-11b81e8e57f6

Run 4 months ago

Stats are not available yet

The run is available. Its result stats will appear here when they are ready.

Repository: huggingface/context-course
Path: projects/inference/.agents/skills/huggingface-local-models/SKILL.md
Commit: 0b4572f

Evaluated: 4 months ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Local Model Setup for a Code Review Assistant Choosing the Right Model for a Memory-Constrained Edge Device Migrating a Research Team's Model to Local Inference

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.