Hugging Face & On-Device Models Cheat Sheet

This content was generated with the assistance of AI and should be verified against the official documentation of each tool and framework before being relied on in production.

This section’s bibliography lists the reference material consulted while preparing these pages.

A single-page index of quick back-links to every page in this sub-section, grouped the same way as the sub-section itself — handy for jumping straight to the topic you need instead of paging through the full navigation.

The downloadable PDF is a separate, single A4 page meant for printing. It states the version baseline this sub-section targets — huggingface_hub 2.0.0 (the hf CLI), transformers 5.17.0, peft 0.21.1, trl 1.14.1, ONNX Runtime 1.30.0, llama.cpp v0.5.0, LiteRT 2.2.0, LiteRT-LM 0.17.1, Transformers.js 4.3.0, Python 3.12, Java 21 with Spring Boot 4.1 and Spring AI 2.0.1, all checked on 2026-09-30 — and covers:

  • the hf CLI commands;

  • the download API (hf_hub_download, snapshot_download) and the cache, token and offline environment variables;

  • the licence checklist;

  • the format → runtime table;

  • the pipeline task names;

  • the curated model table (speech-to-text, text-to-speech, vision, small LLMs and embeddings, with licences);

  • the conversion one-liners per format;

  • the LoRA formula and a TRL SFTTrainer skeleton;

  • the per-platform integration snippets (FastAPI, Spring, Swift, Kotlin, C# and JavaScript);

  • the deprecations and renames.

The Hub — Hugging Face & On-Device Models, Hub Essentials, Choosing Models & Licences and Model Formats.

Python and models — Transformers Pipelines, Speech Models: STT & TTS, Vision Models, Small LLMs & Embeddings, Conversion & Quantization and Fine-Tuning with PEFT & TRL.

Integrating into apps — Python Backends, Java & Spring Boot, Apple Platforms, Android, Windows & .NET, Web & Cross-Platform and Inference Providers & Spaces.

Download the Hugging Face & On-Device Models Cheat Sheet (PDF)

References

The PDF summarizes these official pages; each is cited in full on the page listed above that covers it, and in Hugging Face & On-Device Models' bibliography.

The Hub

Libraries

Runtimes and platforms

Papers