Top Builders

Explore the top contributors showcasing the highest number of app submissions within our community.

Hugging Face Hub

The Hugging Face Hub is an open-source repository platform that hosts over one million machine learning models, datasets, and interactive applications. It serves as the central collaboration layer for the ML community, enabling developers to discover, share, version, and deploy models across every modality including text, vision, audio, and multimodal. Model checkpoints on the Hub are compatible with the Transformers, Diffusers, and Datasets libraries, and can be loaded in a few lines of code.

General
AuthorHugging Face
TypeML Model Repository and Collaboration Platform
Websitehuggingface.co
DocumentationHub Documentation
Repositorygithub.com/huggingface/huggingface_hub
Modelshuggingface.co/models
Datasetshuggingface.co/datasets

Start building with Hugging Face Hub

The Hub is the fastest way to get a pretrained model running in your project. Load any of the 1M+ checkpoints directly into Transformers or Diffusers with a single function call, or browse the Hub to find the right base model for your use case. You can host your own models privately and share fine-tuned adapters with the community without uploading full model weights. During AMD-sponsored hackathons on lablab.ai, participants pull models from the Hub, fine-tune or build on them using AMD Developer Cloud GPUs, and publish their final projects back to the Hub as a Space. Explore what the community has built at Hugging Face Use Cases and Applications.

Hugging Face Hub Tutorials

Getting Started

Key Features

1M+ models Text, vision, audio, multimodal, and specialized domain models from top research teams and companies including Meta, Mistral, Google, and Alibaba Cloud.

Private repositories Host proprietary models and datasets with access controls. Upgrade to a PRO or Enterprise account for private inference endpoints.

Model cards Structured documentation for model limitations, intended use, training details, and evaluation results — standardized across all public checkpoints.

Version control Git-based versioning with LFS support for large files. Every model and dataset on the Hub has a full commit history.

Fine-tuned adapters Share and reuse LoRA and PEFT adapters without uploading full model weights. Adapters reference their base model and load in seconds.

Libraries

  • Transformers Unified API for pretrained models across text, vision, and audio
  • huggingface_hub Python SDK for Hub authentication, uploads, and downloads
  • Datasets Efficient access to Hub datasets with streaming and arrow-based caching
  • PEFT Parameter-efficient fine-tuning (LoRA, QLoRA, prefix tuning)
  • Optimum-AMD Optimized inference and training for AMD hardware via ROCm
Edit on GitHub

huggingface HuggingFace Hub AI technology Hackathon projects

Discover innovative solutions crafted with huggingface HuggingFace Hub AI technology, developed by our community members during our engaging hackathons.

Beacon

Beacon

When the river crests and the towers go dark, a hundred people end up stranded in a school gym with no signal and no way to call for help. A volunteer nurse faces a growing line of the sick and injured with no one to consult. A teacher manages sixty frightened kids alone. A family doesn't know if their water is safe to drink. Every one of them is holding a phone with a powerful on-device NPU, but cloud AI dies the instant the network does, and no single phone has the memory or compute to run a frontier-grade LLM by itself. Beacon is built around this constraint from the start: the model is pre-sharded before disaster strikes, not after. Users opt in ahead of time, downloading a layer-wise slice of a large language model's weights onto their device, a contiguous block of transformer layers sized to that phone's available memory and NPU class. These shards sit dormant on the device, costing nothing until they're needed. When the network goes down, phones nearby connect over a peer-to-peer hotspot network: one phone hosts, others join directly, with no router or internet infrastructure required. Beacon assembles an inference cluster from whichever pre-loaded layer shards happen to be present in the room, sequencing them in the correct layer order for a forward pass. The hotspot link only needs to negotiate which layers are available, route activations between phones in sequence, and reroute around a phone that drops out or runs out of battery. The heavy lifting, distribution, was done in advance, when everyone still had a connection. The result is a cluster that can assemble in seconds during an emergency, because the only real-time job is discovery and coordination, not download. The nurse gets triage guidance. The teacher gets crisis-management support. The family gets a real answer about their water. The help didn't arrive; it was already pre-positioned in their pockets, just waiting to be switched on.

SnapOn: On-Device Context-Aware Multimodal AI

SnapOn: On-Device Context-Aware Multimodal AI

SnapOn is an Android-based, offline-first multimodal AI assistant that understands what the user says and what the user sees. By combining speech, vision, and on-device reasoning, SnapOn provides fast, privacy-preserving assistance without any cloud dependency. Rather than a general-purpose chatbot, SnapOn is designed for real-world situations, identifying people and objects, summarizing documents, recognizing products and labels, and answering spoken questions about the current scene. The interaction is natural and hands-free. Hold the mic button, speak your question or say "remember this," and SnapOn captures the best camera frame, transcribes your voice using Whisper, and generates a grounded answer using SmolVLM-500M-Instruct running on the Snapdragon Hexagon NPU via ExecuTorch. What makes SnapOn unique is its personal memory layer. Say "remember this is my medication Metformin" and SnapOn saves a visual fingerprint using CLIP embeddings alongside your exact words. Next time you point the camera at the same object or person, SnapOn recognizes it passively and surfaces your saved context automatically, no button press needed. Use cases include identifying people and objects in view, summarizing documents and text in the scene, recognizing products, signs, and labels, answering spoken questions, and saving personal context for future reference. The stack includes SmolVLM-500M-Instruct, OpenAI CLIP ViT-B/32, Whisper-tiny, FAISS, SQLite, CameraX, AudioRecord, and Android TTS. On-device compilation targets SM8750 via ExecuTorch and Qualcomm QNN backend. Built for the ExecuTorch Hackathon with a strong emphasis on NPU utilization, real-world usability, and complete privacy.

SixthSense: Haptic Vision for the Blind

SixthSense: Haptic Vision for the Blind

SixthSense is a wearable that helps blind and low-vision people sense obstacles around them and find a clear path. A phone is mounted on the chest and watches the way ahead. On-device models turn what the camera sees into a simple readout: how near obstacles are in the left, center, and right zones, what objects are present, and whether the path is clear. That readout drives a vibration belt worn at the waist, which buzzes on the side of the nearest obstacle so the user can feel which way to move. The point is that knowing something is close is not enough. A basic vibrating cane buzzes whenever anything is near, so in a crowd it buzzes constantly without telling you where the gap is. SixthSense reads each zone separately and steers the user toward open space, so it stays useful in busy areas. The user can also ask what is ahead and hear a short spoken answer, or point the camera at a sign and have its text read aloud. The vision runs on the phone. YOLOv11n detects objects and tags each to a left, center, or right zone. Depth-Anything-V2 estimates how near things are, which sets how hard the belt buzzes. Qwen2.5-0.5B answers spoken questions about the scene, and ML Kit reads text on demand. The models run through ExecuTorch as compiled files on the phone, offline, on a Qualcomm Snapdragon 8 Elite, with the option to run on the Hexagon NPU. The phone sends a small directional packet over Bluetooth to an ESP32, which drives the belt motors. Cost is the main reason it exists. Smart canes and glasses run from about $850 to over $2,000, and only one in ten people who need assistive technology can get it, dropping to about five percent in lower-income countries. SixthSense uses a phone the user already has and a sub-$20 belt, with room to reach about $50 at scale, putting this within reach of people who are priced out today.

Sub Rosa: On-Device AI Legal Intake

Sub Rosa: On-Device AI Legal Intake

Sub Rosa is an Android app that turns a lawyer's first client meeting into clear intake notes. It runs entirely on the phone and never goes online. It records the conversation and transcribes it on the device with Whisper. A small language model, Qwen3-1.7B running with ExecuTorch on the Qualcomm Hexagon NPU, then produces three things: the facts, each shown next to the exact words from the transcript that back it up; the missing items, the standard intake points the client did not mention, found by comparing the talk against a checklist; and a few neutral follow-up questions to ask. The model only reads and sorts what it is given. It never states the law or gives advice. The legal knowledge lives in checklists written by people, not in the model's weights, so a small model stays accurate with no training step. Privacy is built in. The app has no internet permission, so the phone blocks any connection, and an on-screen panel shows nothing was sent. Audio is never saved, and all client data is encrypted on the device with AES-256-GCM.

Data Center Ops

Data Center Ops

Data Center Ops is a real-time, on-device AI assistant that helps data center technicians inspect and assemble server racks correctly the first time. Over 1000 racks are built every week — dense meshes of cables, trays, and ports assembled at volume by labor crews cross-referencing paper guides. Roughly 80% are installed incorrectly on the first attempt. DC-Ops turns any Snapdragon phone into a smart inspection tool: point the camera at a rack and it instantly identifies 16 classes of components — compute trays, network ports, LEDs, cables, fans, drive bays, power shelves, DPUs and more — drawing live overlays on the camera feed. Everything runs entirely on-device using PyTorch and ExecuTorch, compiled to the Qualcomm QNN Hexagon Tensor Processor (HTP) NPU on the Samsung Galaxy S25 Ultra (Snapdragon 8 Elite, SM8750). This matters because data centers that manage private data have limited cloud availability but technicians need instant feedback. By running inference directly on the NPU with INT8 quantization, DC-Ops delivers low-latency, power-efficient detection with zero data ever leaving the device. We trained on 2,036 human-labeled images across four datasets, bootstrapped with a BrightData web-scraping + auto-labeling pipeline (Grounding DINO + SAM). Models and dataset are published openly on Hugging Face.

Scribend: 100% Offline Edge AI Medical Scribe

Scribend: 100% Offline Edge AI Medical Scribe

Scribend addresses the critical need for secure, automated medical documentation in clinical environments where cloud connectivity is inconsistent or data privacy is paramount. By leveraging an entirely on-device Edge AI architecture, Scribend transforms spoken doctor-patient interactions into structured clinical records without ever transmitting data to the cloud. The system utilizes a modular, multi-model pipeline optimized for the Qualcomm Snapdragon NPU: Transcription: We utilize Distil-Whisper Small for high-accuracy speech-to-text, augmented with an 80-term medical vocabulary hint to ensure precise capture of clinical terminology and phonetic typo correction. Context Retrieval: Using MiniLM vector embeddings and a local SQLite database, the system performs semantic searches on a patient’s historical records, providing the LLM with relevant medical context before note generation. Reasoning: Meta Llama 3.2 3B Instruct acts as the system’s "brain." It performs zero-shot speaker diarization to separate Doctor and Patient dialogue, applies contextual logic to identify medical facts, and outputs a perfectly structured JSON SOAP note. Formatting: Finally, the system automatically converts the JSON output into a polished, timestamped Markdown document, complete with tables, bold headers, and bullet points for instant clinical review. Designed specifically for modern mobile hardware like the Samsung Galaxy S25, Scribend achieves this performance with a sub-2.5GB memory footprint, proving that complex, context-aware AI is not only possible but efficient on edge devices