Search across 536 pages

Try a tool name, category, or "lifetime deal"

↑↓ navigate ↵ open Esc close
AI Black Friday Deals
Live directory · Updated weekly · No pay-to-rank

Hugging Face Models: The Complete Directory & Live Ranking

A live directory of Hugging Face Hub models, ranked by real adoption, growth, and maintenance - not opinion.

Alston Antony Curated & maintained by Alston Antony · 15+ yrs SEO, 500+ tools tested
300Models ranked
3949.2MCombined downloads
8Categories
Live data from the Hugging Face Hub API
Ranked by real adoption & growth
No model pays to be listed or ranked
See the full ranking methodology →
Updated November 9, 2026 Hugging Face Hub API 300 models ranked Refreshed weekly Independent & ad-free
What & how

What Is a Hugging Face Model, and How Do You Use One?

What it is

A Hugging Face model is a pretrained AI model (language, vision, speech, or multimodal) published on the Hugging Face Hub, along with a model card documenting its license, training data, and intended use. Anyone can download, fine-tune, or run these models, often for free.

How to use a Hugging Face model

Every model on this list can be loaded directly with the transformers library (AutoModel.from_pretrained("org/model-id")) or downloaded standalone with huggingface_hub's snapshot_download. Click a model's name to open its official Hugging Face page, where the model card documents exact usage, required libraries, and any license terms to accept.

Browse the full directory below ↓

As of November 9, 2026, this is a live, free directory ranking the best and most-adopted models on the Hugging Face Hub by real data. zplatform.ai tracks models that clear a minimum adoption floor (300 ranked today) using the free, public Hugging Face Hub API. Ranked by downloads, likes, and how recently each model was updated - not opinion - and the list refreshes automatically every week. How we choose and rank →

Also explore the ranked Hugging Face datasets directory and the best MCP servers for wiring models into AI apps.

The best Hugging Face models as of November 9, 2026, ranked by our composite score:

  1. MiniMax-H3 - 86.7M downloads, quality score 100/100.
  2. whisperkit-coreml - 135.3M downloads, quality score 98/100.
  3. audio.cpp-gguf - 18.4M downloads, quality score 98/100.
  4. Unlimited-OCR - 14.2M downloads, quality score 97/100.
  5. GLM-5.3-Flash - 14.2M downloads, quality score 97/100.

Every Ranked Model

Every Hugging Face model that clears our adoption floor, scored on a transparent composite of adoption, growth, maintenance, and trust. Select up to 4 to compare side by side.

Compare # Model Category Downloads Likes License Updated Quality
Editor's picks

Best Hugging Face Models by Use Case

Best Text Generation & Chat Models

Ornith-1.5-9B-GGUF and gpt-oss-120b-GGUF top the text-generation category, the models behind most chat assistants and text-completion tools built on Hugging Face.

  1. Ornith-1.5-9B-GGUF 95/100 quality
  2. gpt-oss-120b-GGUF 94/100 quality
  3. NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 94/100 quality

Best Image Generation Models

Z-Image-Lora and Qwen-Image-2.1 lead text-to-image generation on Hugging Face.

  1. Z-Image-Lora 93/100 quality
  2. Qwen-Image-2.1 88/100 quality
  3. Flux-2-Dev 87/100 quality

Best Vision & Multimodal Models

Unlimited-OCR and GLM-5.3-Flash lead the vision-language models on Hugging Face, handling image understanding, visual question answering, and multimodal chat in one model.

  1. Unlimited-OCR 97/100 quality
  2. GLM-5.3-Flash 97/100 quality
  3. Huihui-Qwen3.8-27B-abliterated-GGUF 96/100 quality

Best Embedding & Retrieval Models

bert-base-turkish-cased-mean-nli-stsb-tr and all_miniLM_L6_v2_with_attentions lead embeddings and retrieval, turning text into vectors for semantic search, RAG pipelines, and re-ranking.

  1. bert-base-turkish-cased-mean-nli-stsb-tr 91/100 quality
  2. all_miniLM_L6_v2_with_attentions 86/100 quality
  3. bge-small-en-v1.5-onnx-Q 85/100 quality

Best Tabular, Time-Series & Robotics Models

chronos-2 and timesfm-3.0-pytorch lead this emerging mix of tabular, time-series forecasting, and robotics models.

  1. chronos-2 93/100 quality
  2. timesfm-3.0-pytorch 87/100 quality
  3. chronos-2 83/100 quality

Best Speech & Audio Models

whisperkit-coreml and audio.cpp-gguf top speech and audio, covering transcription, text-to-speech, and audio classification.

  1. whisperkit-coreml 98/100 quality
  2. audio.cpp-gguf 98/100 quality
  3. parakeet-unified-en-0.6b-gguf 96/100 quality

Best Text Classification Models

finbert and laya top text classification and understanding tasks like sentiment, masked-token prediction, and named-entity tagging.

  1. finbert 90/100 quality
  2. laya 85/100 quality
  3. glotlid 84/100 quality
Browse

Browse by Category

Vision & Multimodal

96 models · 1967.9M downloads

Filter the directory to Vision & Multimodal ↓

Text Generation & Chat

76 models · 246.4M downloads

Filter the directory to Text Generation & Chat ↓

Embeddings & Retrieval

15 models · 216.6M downloads

Filter the directory to Embeddings & Retrieval ↓

Speech & Audio

31 models · 306.9M downloads

Filter the directory to Speech & Audio ↓

Image Generation

17 models · 92.5M downloads

Filter the directory to Image Generation ↓

Text Classification & Understanding

10 models · 253.7M downloads

Filter the directory to Text Classification & Understanding ↓

Tabular, Time-Series & Robotics

3 models · 302.1M downloads

Filter the directory to Tabular, Time-Series & Robotics ↓

Other

52 models · 563.1M downloads

Filter the directory to Other ↓

State of the Models Ecosystem

Most Popular

  1. mobilenetv3_small_100.lamb_in1k 1189.5M
  2. chronos-2 194.8M
  3. whisperkit-coreml 135.3M
  4. finbert 127.0M
  5. roberta-base-go_emotions 106.9M
  6. chronos-2 104.9M
  7. Qwen3-Embedding-0.6B 102.8M
  8. Wan-2.2 100.7M
  9. MiniMax-H3 86.7M
  10. WanVideo_comfy 76.3M

Fastest Growing (30-day downloads trend)

  1. GLM-5.3-Flash +524.4%
  2. Qwen3.8-Flash-Next +515.4%
  3. whisperkit-coreml +343.1%
  4. MiniMax-H3-GGUF +317%
  5. VieNeu-TTS-v3-Turbo +292.8%
  6. GLM-5.3 +265.3%
  7. audio.cpp-gguf +249.8%
  8. Qwen3-VL +246.2%
  9. chronos-2 +226.3%
  10. OmniVoice +196.8%

By Category

  1. Vision & Multimodal 96 · 1967.9M
  2. Text Generation & Chat 76 · 246.4M
  3. Other 52 · 563.1M
  4. Speech & Audio 31 · 306.9M
  5. Image Generation 17 · 92.5M
  6. Embeddings & Retrieval 15 · 216.6M
  7. Text Classification & Understanding 10 · 253.7M
  8. Tabular, Time-Series & Robotics 3 · 302.1M

How we rank, and why you can trust it

  • Data source: the free, public Hugging Face Hub API (downloads, likes, license, and last-modified date for every model). Refreshed weekly.
  • Inclusion is automatic: a model must clear an adoption floor - at least 1,000 downloads in the last 30 days, or at least 50 likes - so the list stays credible rather than padded with unused uploads. We do not hand-pick winners.
  • Adoption is measured by all-time downloads (when available) and likes, log-scaled so a handful of enormous outliers do not flatten the rest of the ranking.
  • Growth is measured by the 30-day change in downloads, compared against our own weekly snapshots - shown once enough history has accrued. Hugging Face also exposes an internal "trending score," but its scale is not publicly documented, so it is shown for reference only and does not drive the ranking.
  • Maintenance reflects how recently a model was updated - a model updated in the last 30 days scores highest, decaying the longer it has gone untouched.
  • Ranking is data-driven only. No model pays to be listed or ranked.

The Quality Score formula

The Quality Score (0-100) is a transparent weighted blend: 40% Adoption (downloads and likes, log-scaled), 20% Growth (30-day downloads trend), 25% Maintenance (how recently the model was updated), and 15% Trust (a stated license, an identified author, and not being access-gated).

Frequently asked questions

What are the best Hugging Face models?

The best Hugging Face models by our composite data score are listed in the leaderboard above, ranked on adoption, growth, and maintenance rather than opinion. Use the filters to narrow by task category.

How is this different from Hugging Face's own trending page?

Hugging Face's own trending view surfaces short-term spikes. This directory instead weighs sustained adoption (downloads and likes) alongside how actively a model is maintained, so the ranking favors models that are genuinely being used, not just currently trending.

Are Hugging Face models free to use?

Most models on the Hugging Face Hub are free and open-weight, though licenses vary (Apache 2.0, MIT, and custom licenses like Llama's are all common). Some models are "gated" and require accepting terms before download. Each row shows the license when Hugging Face reports one.

How often is this list updated?

This directory refreshes weekly, pulling fresh downloads, likes, and maintenance data directly from the Hugging Face Hub API.

How many models are on the Hugging Face Hub?

The Hugging Face Hub hosts well over a million models. This directory ranks the 300 that clear our adoption floor (at least 1,000 downloads in 30 days, or 50 likes), as of November 9, 2026.

See also: Hugging Face Datasets, ranked, MCP Servers directory, and WordPress AI Plugins directory.

Last updated: . Data from the Hugging Face Hub API. See the methodology and the machine-readable data.json.