---
title: "HuggingFace Best Model Finder"
type: skill
id: "huggingface-skills/hub-and-models/huggingface-best"
category: "AI & machine learning"
publisher: "Hugging Face"
license: "Apache-2.0"
source: "https://github.com/huggingface/skills/tree/25910b3"
canonical: "https://labs.pho.chat/en/skills/huggingface-skills/hub-and-models/huggingface-best"
open_in_pho: "https://pho.chat/customize?item=huggingface-skills%2Fhub-and-models%2Fhuggingface-best&utm_source=labs&utm_medium=skill-page&utm_campaign=skills-library"
---

# HuggingFace Best Model Finder

Use when the user asks about finding the best, top, or recommended model for a task, wants to know what AI model to use, or wants to compare models by benchmark scores. Triggers on: "best model for X", "what model should I use for", "top models for [task]", "which model runs on my laptop/machine/device", "recommend a model for", "what LLM should I use for", "compare models for", "what's state of the art for", or any question about choosing an AI model for a specific use case. Always use this skill when the user wants model recommendations or comparisons, even if they don't explicitly mention HuggingFace or benchmarks.

Source: Hugging Face (Apache 2.0), copied at a pinned commit. Free to use. Part of the Phở Skills library (https://labs.pho.chat/en/skills).
Skill set: Hugging Face Hub and models (https://labs.pho.chat/en/skills/huggingface-skills/hub-and-models.md).

## What it covers
- Step 1: Parse the request
  - Device → max parameter budget
- Step 2: Find relevant benchmark datasets
- Step 3: Fetch top models from leaderboards
- Step 4: Enrich with model metadata
- Step 5: Filter and rank
- Step 6: Output
  - Comparison table
  - Follow-up
- Error handling

## Other skills in this set
- [Hf mem](https://labs.pho.chat/en/skills/huggingface-skills/hub-and-models/hf-mem.md): Hugging Face CLI to estimate the required memory to load Safetensors or GGUF model weights for inference from the Hugging Face Hub
- [Hugging Face Local Models](https://labs.pho.chat/en/skills/huggingface-skills/hub-and-models/huggingface-local-models.md): 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…
- [Transformers.js - Machine Learning for JavaScript](https://labs.pho.chat/en/skills/huggingface-skills/hub-and-models/transformers-js.md): Use Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript. Supports NLP (text classification, translation, summarization), computer vision (image…
- [Hugging Face Dataset Viewer](https://labs.pho.chat/en/skills/huggingface-skills/hub-and-models/huggingface-datasets.md): Use this skill for Hugging Face Dataset Viewer API workflows that fetch subset/split metadata, paginate rows, search text, apply filters, download parquet URLs, and read size or statistics.
- [Hugging Face Paper Pages](https://labs.pho.chat/en/skills/huggingface-skills/hub-and-models/huggingface-papers.md): Look up and read Hugging Face paper pages in markdown, and use the papers API for structured metadata such as authors, linked models/datasets/spaces, Github repo and project page. Use when the user…
- [Hf cli](https://labs.pho.chat/en/skills/huggingface-skills/hub-and-models/hf-cli.md): Hugging Face Hub CLI (`hf`) for downloading, uploading, and managing models, datasets, spaces, buckets, repos, papers, jobs, and more on the Hugging Face Hub. Use when: handling authentication…
- [TRL](https://labs.pho.chat/en/skills/huggingface-skills/hub-and-models/trl-training.md): Post-train LLMs with TRL (Transformers Reinforcement Learning) — SFT, DPO, GRPO, KTO, and reward-model training. Use when writing or debugging training code with the TRL Python API or the trl CLI.
- [Trackio - Experiment Tracking for ML Training](https://labs.pho.chat/en/skills/huggingface-skills/hub-and-models/huggingface-trackio.md): Track and visualize ML training experiments with Trackio. Use when logging metrics during training (Python API), firing alerts for training diagnostics, or retrieving/analyzing logged metrics (CLI)…
- [SageMaker Deployment Planner](https://labs.pho.chat/en/skills/huggingface-skills/hub-and-models/hf-cloud-sagemaker-deployment-planner.md): Plan and coordinate the deployment of a model to Amazon SageMaker AI. Use this skill whenever the user wants to deploy, host, serve, or expose a model on SageMaker or AWS — including phrases like…

## Use it
- In Phở: open https://pho.chat/customize?item=huggingface-skills%2Fhub-and-models%2Fhuggingface-best&utm_source=labs&utm_medium=skill-page&utm_campaign=skills-library and press Try, or add it so Phở loads it whenever a request matches. Phở works with your own API key (OpenAI, Anthropic, Google and others).
- Full instructions (original SKILL.md, unchanged): https://labs.pho.chat/skills/raw/huggingface-skills/hub-and-models/skills/huggingface-best/SKILL.md
- Original files: https://github.com/huggingface/skills/tree/25910b3 (Apache 2.0).
- Full machine-readable index: https://labs.pho.chat/skills.json