4.6k
LMArena Leaderboard
π
Display LMArena Leaderboard
LLM Tools
A collection of tools as various HF Spaces on LLMs.
-
-
13.5k
Open LLM Leaderboard
πTrack, rank and evaluate open LLMs and chatbots
-
1.09k
OpenVoice
π€ -
191
Yet Another LLM Leaderboard
πDisplay interactive web apps
-
77
Phixtral Chat
π -
144
Hallucinations Leaderboard
π₯View and submit LLM evaluations
-
380
WhisperSpeech
π¬ -
219
Chunk Visualizer
π«Pick a text splitter => visualize chunks. Great for RAG.
-
114
Modelcard Creator
β‘Create and upload a Hugging Face model card
-
555
LLM-Perf Leaderboard
πExplore hardware performance for LLMs
-
94
LLM Safety Leaderboard
π₯View and submit machine learning model evaluations
-
209
LLaMA Board
π¦Fine-tuning large language model with Gradio UI
-
954
ReplaceAnything
πReplace objects in images using prompts or reference images
-
72
AutoMerger
βΎ -
827
Parler-TTS
π₯High-fidelity Text-To-Speech
-
98
GLiNER-Multiv2.1
π»Identify named entities in text
-
61
Ratchet + Phi
πGenerate answers to your questions
-
167
IDEFICS2 Playground
π¨ -
313
PaliGemma Demo
π€²Annotate and describe images with text prompts
-
172
GLiNER-medium-v2.1, zero-shot NER
π»Identify key entities in text
-
82
GLiNER HandyLab
β‘Explore multiple text tasks with GLiNER HandyLab
-
696
Qwen2 72B Instruct
π»Chat with a helpful assistant using text input
-
92
PDF to Dataset
πConvert PDFs to a dataset and upload to Hugging Face
-
86
Instruction Synthesizer
πGenerate instruction-response pairs from text
-
1.62k
GGUF My Repo
π¦Create quantized models from Hugging Face
-
166
MeshAnything
πGenerate artist-created 3D mesh from input mesh
-
60
Mars5 Space
π -
163
InternLM XComposer
π’Display a web page
-
38
Built-in AI Chat
πRun Gemini Nano locally in your browser with Transformers.js
-
15
Florence 2
πGenerate answers from images and questions
-
570
The Tokenizer Playground
πExperiment with and compare different tokenizers
-
302
Whisper Speaker Diarization
π£Separate speakers in audio recordings
-
572
NIST FRVT TOP 1 Face Recognition, Face Liveness Detection, Face Analysis
π₯Compare and analyze faces in images
-
127
Segment Anything 2
π₯Segment objects in images using prompts
-
106
Vision Papers
π»All paper summaries read by Merve
-
4.96k
FLUX.1 [Schnell]
πGenerate images from text prompts
-
9.04k
FLUX.1 [dev]
π₯Generate images from text prompts
-
53
WebLLM Playground
πDisplay a React app with TypeScript
-
5
Pdf Reader
πSummarize text from PDF URLs
-
65
Falcon Mamba Playground
πGenerate chat responses using FalconMamba-7b model
-
162
LongWriter
π¬LLM for long context
-
115
Llama3.1 S V0.2 Checkpoint 2024 08 20
π»Convert text to audio and vice versa
-
123
Candle Phi Wasm Demo
π―Generate text based on prompts
-
271
Latent Navigation
πͺTravel through the model latent space
-
11
reviewer-arena
πReview academic papers by comparing model-generated evaluations
-
81
Semantic Hugging Face Hub Search
πFind datasets and models using semantic search
-
255
Convert to Safetensors
πΆConvert models to Safetensors and open PRs
-
629
OpenAudio S1
πGenerate speech from text
-
coreml-projects/sam-2-studio
Updated β’ 25 -
dleemiller/word-llama-l2-supercat
Updated β’ 92 -
450
PDF2Audio
πTransform text into engaging podcast dialogues or detailed reports
-
3
Gemini 1.5 Flash 8b Exp 0924
πEngage in a conversation with a chatbot
-
221
Whisper WebGPU
π€Convert spoken words to text
-
964
Whisper Turbo
π€―Transcribe audio or YouTube videos into text
-
14
Rag Highlights
πRAG with source links inserted using LXT library.
-
359
GOT Online
π¬Extract text from images using various OCR modes
-
196
Kotaemon
πAsk questions and get detailed answers
-
38
Semantic Deduplication
π§ΉDeduplicate HuggingFace datasets in seconds
-
64
Ichigo Llama3.1 S Instruct
π’Generate text from audio recordings
-
77
NuExtract 1.5
πPlayground for NuExtract-v1.5
-
143
Qwen 2.5 Code Interpreter
πExecute code snippets and get results
-
224
PROMPT++
βRefine your prompts
-
321
Aya Models
πInteract with the Aya family of models.
-
104
Open LLM Leaderboard Model Comparator
πCompare Open LLM Leaderboard results
-
17
BitNet.cpp
π»Display a loading screen with a spinner
-
143
MLX My Repo
πConvert and upload Hugging Face models to MLX format
-
69
Vectorsearch Hub Datasets
π₯Add vectors to Hub datasets and do in memory vector search.
-
sentence-transformers-testing/stsb-bert-tiny-lora
Sentence Similarity β’ Updated β’ 3 -
38
Talk To Ultravox
β‘Talk to Fixie.ai's Ultravox with WebRTC β‘οΈ
-
19
Hub LFS Analysis
πAn analysis of LFS files on the Hub.
-
164
DocLayout YOLO
πDemo for DocLayout-YOLO
-
109
Llmlingua 2
π»Compress lengthy prompts into shorter versions while preserving key information
-
86
InstantIR
πΌdiffusion-based Image Restoration model
-
168
Flux IP Adapter
πΌPrompt with Images in flux[dev]
-
55
Github Issue Generator
π§Generate structured GitHub issues
-
48
Paligemma2 Vqav2
π¨PaliGemma2 LoRA finetuned on VQAv2
-
10
Keras Chatbot Battle
π¬Interact with multiple chatbots simultaneously
-
686
Qwen2.5
πChat with Qwen, an AI assistant
-
24
StoryStar
π¬Fantasy story generator
-
292
Jupyter Agent
πGenerate interactive Jupyter notebooks with user input
-
923
QwQ-32B-Preview
πQwQ-32B-Preview
-
1.66k
Qwen2.5 Coder Artifacts
π’Generate code for applications
-
9
Transformers Pipeline Playground
πSearch, load and play with transformer pipelines
-
455
Stable Point-Aware 3D
β‘Create 3D models from single images
-
15
Fairly Multilingual ModernBERT Token Alignment
πAligns the tokens of two sentences
-
2.9k
Kokoro TTS
β€Upgraded to v1.0!
-
228
Llama 3.2 Reasoning WebGPU
π§Small and powerful reasoning LLM that runs in your browser
-
113
MiniMaxText01
π¬Communicate with a multimodal chatbot
-
27
Naive RAG Chatbot
πQuickest way to test naive RAG run with AutoRAG.
-
549
DeepSeek-R1 WebGPU
π§Next-generation reasoning model that runs locally in-browser
-
65
SmolVLM
πGenerate descriptions from images and text prompts
-
214
Janus Pro WebGPU
πIn-browser unified multimodal understanding and generation.
-
145
Agent Data Analyst
π€Need to analyze data? Let a Llama-3.1 agent do it for you!
-
309
Kokoro TTS Zero
π΄β¨[With v1.0.0] Accelerated TTS on Kokoro-82M
-
574
First Agent Template
β‘Get current time in any timezone
-
91
Paligemma2 Mix
πGenerate text and segment images using PaliGemma 2
-
3.14k
The Ultra-Scale Playbook
πThe ultimate guide to training LLM on large GPU Clusters
-
3
marimo github notebooks on the fly
βCollection of marimo notebooks from a GitHub repository
-
2
Fastphone
πDownload and run an app from a Hugging Face repository
-
45
Magma UI
πMagma-8B model for UI Agents
-
8
Deepseek Ai DeepSeek R1 Distill Qwen 32B
β‘Generate responses to your questions
-
625
DiβͺβͺRhythm
πΆBlazingly Fast and Embarrassingly Simple Song Generation
-
7
Radial Plot Generator
πΈGenerate radial plots for language model performance
-
10
OpenStreetMap AI Helper
πContributing to OpenStreetMap with the help of AI
-
82
DeTikZify
πConvert images and sketches into graphics programs with TikZ
-
2
Bulk
πA bulk labelling interface for binary text classification
-
12.6k
DeepSite v2
π³Generate any application with DeepSeek
-
37
YourBench Advanced Usage
πExplore advanced functionalities in a clonable space
-
1.66k
Dia 1.6B
π―Generate realistic dialogue from a script, using Dia!
-
766
Qwen3 Demo
πGenerate responses to text prompts in a chat interface
-
115
PlayDiffusion
π¨Generate modified audio from text and voice
-
211
Conversational WebGPU
π -
1.39k
Chatterbox TTS
πΏExpressive Zeroshot TTS
-
530
Sheets
πCreate and enrich datasets using AI
-
22
Leaderboard: Physical Reasoning from Video
πSubmit model evaluations and view leaderboard results
-
34
Nanonets Ocr S
πhttps://nanonets.com/research/nanonets-ocr-s/
-
12
Gemma3n Visual (Audio) Question Answering
π»Visual Audio Question Answering
-
110
Qwen3 MT Demo
πTranslate text between multiple languages
-
126
OCR2
π»nanonets ocr / smoldocling / monkey ocr / typhoon ocr
-
491
Image To Prompt
π»Generate detailed captions for images
-
265
GPT-OSS-120B on AMD MI300X
π»gpt-oss-120b + web browsing + reasoning on AMD MI300X GPUs
-
442
Qwen Image Edit
βEdit images based on user instructions
-
16
Example Leaderboard Template
π₯Duplicate this leaderboard to initialize your own!
-
214
MatchAnything
π’Find matching images based on input criteria
-
2.62k
Anycoder
π’Generate HTML code for web applications
-
252
FastVLM WebGPU
πReal-time video captioning powered by FastVLM