New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Official agent skill

Hugging Face Best Model Finder

by huggingface in huggingface/skills

Finds top models for a task from official Hugging Face benchmark leaderboards, filters them to what fits your hardware, and returns a comparison table with scores.

OfficialApache-2.0Auto-check passedAI & LLM Engineering

Install Hugging Face Best Model Finder

skills CLI
$ npx skills add huggingface/skills --skill huggingface-best -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install huggingface/skills huggingface-best --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/huggingface/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/huggingface-best .claude/skills/huggingface-best && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
huggingface-best
GitHub stars
11k
Used in
2 other repos
Token cost
~1.5k tokens
SKILL.md length
581 words
Files
1
Skills in repo
25
Repo updated
First seen
Licence
Apache-2.0

At a glance

Finds top models for a task from official Hugging Face benchmark leaderboards, filters them to what fits your hardware, and returns a comparison table with scores.

  • Works in 6 steps: Parse the request → Find relevant benchmark datasets → Fetch top models from leaderboards → …
  • Picking a model for a task such as OCR, coding or speech recognition
  • SKILL.md covers Step 1: Parse the request, Step 2: Find relevant…, Step 3: Fetch top models from… and Step 4: Enrich with model…, plus 3 more sections
  • Calls jq, curl and hf; reaches huggingface.co

What it does

The skill reads your request for a task (coding, math and reasoning, chat, OCR, retrieval, speech recognition, image classification and similar) and for any device limit. When a device is named, it works out a parameter budget from the available memory: roughly the memory in GB divided by two for fp16 models, or multiplied by two for Q4 quantized ones. With no device given, it skips filtering and ranks by performance alone.

It then lists the official benchmark datasets through the Hugging Face API, picks every one relevant to the task, and pulls the top entries from each leaderboard, skipping any that return errors and noting them in the output. The leading candidates are enriched with model metadata such as size and tags, and the result is a comparison table of benchmark scores. Requests use curl and jq with a token read from the local Hugging Face cache.

When your agent uses it

  • Picking a model for a task such as OCR, coding or speech recognition
  • Finding which models fit a laptop or GPU with limited memory
  • Comparing candidate models by official benchmark scores

Example prompts

  • “What's the best model for OCR that runs on a 16GB MacBook?”
  • “Recommend a coding model for my RTX GPU with 24GB of VRAM.”
  • “Compare the top speech recognition models by benchmark score.”

Requirements

  • Network access to the Hugging Face API
  • A Hugging Face token at ~/.cache/huggingface/token
  • curl and jq

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Parse the request
  2. Find relevant benchmark datasets
  3. Fetch top models from leaderboards
  4. Enrich with model metadata
  5. Filter and rank
  6. Output

What it can do on your machine

Read from SKILL.md and the folder at commit c3ff942. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • jq
    • curl
    • hf

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • huggingface.co

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Hugging Face Best Model Finder loads about 1.5k tokens when it runs. Until then it costs about 161 tokens; SKILL.md has 581 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~161
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from huggingface/skills at commit c3ff942, republished under its Apache-2.0 licence (© huggingface). 581 words, ~1,453 tokens.

Download SKILL.mdSave it as .claude/skills/huggingface-best/SKILL.md (or your agent's skills folder).
name
huggingface-best
description
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.

HuggingFace Best Model Finder

Finds the best models for a task by querying official HF benchmark leaderboards, enriching results with model size data, filtering for what fits on the user's device, and returning a comparison table with benchmark scores.

Step 1: Parse the request

Extract from the user's message:

  • Task: what they want the model to do (coding, math/reasoning, chat, OCR, RAG/retrieval, speech recognition, image classification, multimodal, agents, etc.)
  • Device: hardware constraints (MacBook M-series 8/16/32/64GB unified memory, RTX GPU with VRAM amount, CPU-only, cloud/no constraint, etc.)

If device is not mentioned, skip filtering entirely and return the highest-performing models regardless of size. If the task is genuinely ambiguous, ask one clarifying question.

Device → max parameter budget

When a device is specified, extract its available memory (unified RAM for Apple Silicon, VRAM for discrete GPUs) and apply:

  • fp16 max params (B) ≈ memory (GB) ÷ 2
  • Q4 max params (B) ≈ memory (GB) × 2

Examples: 16GB → 8B fp16 / 32B Q4 — 24GB VRAM → 12B fp16 / 48B Q4 — 8GB → 4B fp16 / 16B Q4

Step 2: Find relevant benchmark datasets

Fetch the full list of official HF benchmarks:

bash
curl -s -H "Authorization: Bearer $(cat ~/.cache/huggingface/token)" \
  "https://huggingface.co/api/datasets?filter=benchmark:official&limit=500" | jq '[.[] | {id, tags, description}]'

Read the returned list and select the datasets most relevant to the user's task — match on dataset id, tags, and description. Use your judgment; don't limit yourself to 2-3. Aim for comprehensive coverage: if 5 benchmarks clearly cover the task, use all 5.

Step 3: Fetch top models from leaderboards

For each selected benchmark dataset:

bash
curl -s -H "Authorization: Bearer $(cat ~/.cache/huggingface/token)" \
  "https://huggingface.co/api/datasets/<namespace>/<repo>/leaderboard" | jq '[.[:15] | .[] | {rank, modelId, value, verified}]'

Collect model IDs and scores across all benchmarks. If a leaderboard returns an error (404, 401, etc.), skip it and note it in the output.

Step 4: Enrich with model metadata

For the top 10-15 candidate model IDs, get model infos.

bash
# REST API
curl -s -H "Authorization: Bearer $(cat ~/.cache/huggingface/token)" \
  "https://huggingface.co/api/models/org/model1" | jq '{safetensors, tags, cardData}'

# CLI (hf-cli)
hf models info org/model1 --json | jq '{safetensors, tags, cardData}'

Extract from each response:

  • Parameters: safetensors.total → convert to B (e.g., 7_241_748_480 → "7.2B")
  • License: from model card tags (look for license:apache-2.0, license:mit, etc.)
  • If safetensors is absent, parse size from the model name (look for "7b", "8b", "13b", "70b", "72b", etc.)
Show full SKILL.md (264 more words)Show less

Step 5: Filter and rank

If a device was specified:

  1. Remove models exceeding the fp16 parameter budget for the device
  2. Flag models that fit only with Q4 quantization (multiply budget by ~4 for Q4 capacity)
  3. If a highly-ranked model is slightly over budget, keep it with a "needs Q4" note — don't silently drop it

If no device was mentioned: skip all size filtering — just rank by benchmark score.

Then: rank by benchmark score (descending), keep top 5-8 models.

Include proprietary models (GPT-4, Claude, Gemini) if they appear on leaderboards, but flag them as "API only / not self-hostable". If the user explicitly asked for local/open models only, exclude them.

Step 6: Output

Comparison table
markdown
| # | Model | Params | [Benchmark 1] | [Benchmark 2] | License | On device |
|---|-------|--------|--------------|--------------|---------|-----------|
| ⭐1 | [org/name](https://huggingface.co/org/name) | 7B | 85.2% | — | Apache 2.0 | Yes (fp16) |
| 2 | [org/name](https://huggingface.co/org/name) | 13B | 83.1% | 71.5% | MIT | Q4 only |
| 3 | [org/name](https://huggingface.co/org/name) | 70B | 90.0% | 81.0% | Llama | Too large |
  • Link model names to https://huggingface.co/<model_id>
  • Use — for benchmarks where the model wasn't evaluated
  • Star the top recommended pick with ⭐
  • "On device" values: Yes (fp16), Q4 only, Too large, API only
Follow-up

After presenting the table, ask the user: "Would you like to run [top recommended model]?"

If they say yes, ask whether they'd prefer to:

Error handling

  • Leaderboard not found: skip, note "leaderboard unavailable" in output
  • Model missing from hub_repo_details: fall back to parsing size from model name
  • No benchmarks found for task: use the curated fallback table above, or try hub_repo_search with filters=["<task>"] sorted by trendingScore
  • All leaderboards fail: fall back to hub_repo_search for popular models tagged with the task, note that results are by popularity rather than benchmark score

© huggingface, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/huggingface-best of huggingface/skills.

Open the folder on GitHubat commit c3ff942

Used in 2 other repositories

We found 7 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 2 other GitHub owners. This page covers the copy in huggingface/skills, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Hugging Face Best Model Finder next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Hugging Face Best Model Finder compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Hugging Face Best Model Finder this skillhuggingface/skills11k2 repos~1.5kAutomated safety check: PassApache-2.0
LLM Benchmarking with lm-evaluation-harnessOrchestra-Research/AI-Research-SKILLs13k8 repos~3kAutomated safety check: PassMIT
Code Model Evaluation HarnessOrchestra-Research/AI-Research-SKILLs13k4 repos~2.9kAutomated safety check: PassMIT
Hugging Face Community Evalshenryalouf/ruflow157—~1.6kAutomated safety check: PassMIT
Hugging Face Community Evalssickn33/agentic-awesome-skills47k1 repos~1.9kAutomated safety check: PassApache-2.0
Huggingface Community Evalssickn33/agentic-awesome-skills47k1 repos~1.7kAutomated safety check: PassMIT

Similar skills

  • LLM Benchmarking with lm-evaluation-harness

    Orchestra-Research/AI-Research-SKILLs

    Runs lm-evaluation-harness to benchmark language models on academic suites such as MMLU, GSM8K and HumanEval, compare models and track training checkpoints.

    13k GitHub starsUsed in 8 repos~3k tokens
    AI & LLM EngineeringAuto-check passed

  • Code Model Evaluation Harness

    Orchestra-Research/AI-Research-SKILLs

    Benchmarks code generation models with the BigCode Evaluation Harness across HumanEval, MBPP, MultiPL-E and other suites using pass@k metrics.

    13k GitHub starsUsed in 4 repos~2.9k tokens
    AI & LLM EngineeringAuto-check passed

  • Hugging Face Community Evals

    henryalouf/ruflow

    Run local evaluations for Hugging Face Hub models with inspect-ai or lighteval.

    157 GitHub stars~1.6k tokensUpdated 4 mo ago
    AI & LLM EngineeringAuto-check passed

  • Hugging Face Community Evals

    sickn33/agentic-awesome-skills

    Run evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware.

    47k GitHub starsUsed in 1 repo~1.9k tokens
    AI & LLM EngineeringAuto-check passed

  • Huggingface Community Evals

    sickn33/agentic-awesome-skills

    Curated upstream guidance for Huggingface Community Evals; use when the workflow matches the user goal.

    47k GitHub starsUsed in 1 repo~1.7k tokens
    AI & LLM EngineeringAuto-check passed

  • Upload Post Image

    huggingface/blog

    Official

    A skill your agent uses when adding or migrating non-thumbnail images for a Hugging Face Blog post.

    3.5k GitHub stars~1.1k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

More from huggingface/skills

All 25 skills in this repo

  • SageMaker IAM Role Preflight

    huggingface/skills

    Official

    Finds or validates a usable SageMaker execution role before deploying or training, so scripts do not try to create IAM roles they lack permission to create.

    11k GitHub starsUsed in 1 repo~1.8k tokens
    Auto-check passed

  • SageMaker Serving Image Selection

    huggingface/skills

    Official

    Chooses the right serving container and current image URI for deploying a Hugging Face model to a SageMaker endpoint, preferring Hugging Face images over generic ones.

    11k GitHub starsUsed in 1 repo~4.6k tokens
    Auto-check passed

  • Sentence-Transformers Training Router

    huggingface/skills

    Official

    Routes a sentence-transformers training task to the right model type and required reference docs and example scripts, covering bi-encoders, rerankers, sparse and multi-vector models.

    11k GitHub starsUsed in 1 repo~2.6k tokens
    Auto-check passed

  • Python Environment Setup for SageMaker

    huggingface/skills

    Official

    Sets up an isolated Python environment with a supported interpreter and current boto3 before any SageMaker deployment, training or AWS automation code runs.

    11k GitHub starsUsed in 2 repos~1.7k tokens
    Auto-check passed

  • Hugging Face Local Model Evals

    huggingface/skills

    Official

    Runs evaluations of Hugging Face Hub models on local hardware with inspect-ai or lighteval, and helps choose between vLLM, Transformers and accelerate backends.

    11k GitHub starsUsed in 2 repos~1.6k tokens
    Auto-check passed

  • SageMaker Production Defaults

    huggingface/skills

    Official

    Deploys SageMaker endpoints with autoscaling, CloudWatch alarms and tags on by default, using scripts for real-time, scale-to-zero and async setups.

    11k GitHub starsUsed in 1 repo~6.9k tokens
    Auto-check passed

Works with

Categories

Questions about Hugging Face Best Model Finder

What does Hugging Face Best Model Finder do?

Finds top models for a task from official Hugging Face benchmark leaderboards, filters them to what fits your hardware, and returns a comparison table with scores. The skill reads your request for a task (coding, math and reasoning, chat, OCR, retrieval, speech recognition, image classification and similar) and for any device limit. When a device is named, it works out a parameter budget from the available memory: roughly the memory in GB divided by two for fp16 models, or multiplied by two for Q4 quantized ones.

When should I use Hugging Face Best Model Finder?

Hugging Face Best Model Finder fits situations like: picking a model for a task such as OCR, coding or speech recognition; finding which models fit a laptop or GPU with limited memory; comparing candidate models by official benchmark scores.

How do I install Hugging Face Best Model Finder in Claude Code?

Run `npx skills add huggingface/skills --skill huggingface-best -a claude-code`. Or copy the skill folder (skills/huggingface-best in huggingface/skills) into .claude/skills/huggingface-best in your project. Claude Code loads it when a task matches its description.

How do I install Hugging Face Best Model Finder in Codex?

Run `npx skills add huggingface/skills --skill huggingface-best -a codex`. Or copy the skill folder (skills/huggingface-best in huggingface/skills) into .agents/skills/huggingface-best in your project. Codex loads it when a task matches its description.

Can I use Hugging Face Best Model Finder in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add huggingface/skills --skill huggingface-best -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/huggingface-best, .gemini/skills/huggingface-best, .github/skills/huggingface-best and .opencode/skills/huggingface-best in your project.

What does Hugging Face Best Model Finder need to run?

Going by SKILL.md and its folder, Hugging Face Best Model Finder needs the command-line tools its instructions call (jq, curl and hf). Our summary lists: Network access to the Hugging Face API; A Hugging Face token at ~/.cache/huggingface/token; curl and jq.

Does Hugging Face Best Model Finder access the network?

SKILL.md names 1 domain. In commands or code: huggingface.co; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Hugging Face Best Model Finder safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Hugging Face Best Model Finder use?

Hugging Face Best Model Finder is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Hugging Face Best Model Finder use?

About 1.5k tokens (SKILL.md is roughly 5.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Hugging Face Best Model Finder?

Skills that share tags, products or a category with Hugging Face Best Model Finder: LLM Benchmarking with lm-evaluation-harness (Orchestra-Research/AI-Research-SKILLs, 13k stars), Code Model Evaluation Harness (Orchestra-Research/AI-Research-SKILLs, 13k stars), Hugging Face Community Evals (henryalouf/ruflow, 157 stars) and Hugging Face Community Evals (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Hugging Face Best Model Finder?

huggingface (a GitHub organization, an official publisher) maintains it in huggingface/skills, which has 11,151 GitHub stars. The repository holds 25 skills in this directory. The repository was last updated on October 8, 2026.

Source: huggingface/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.