Small LMs
- 🐋
MonadGPT
💬Mistral-7B
😻- 1
Voice Chat With Mistral 7B
🌪 Qwen VL
⚡ChatGLM 6B
🏃Koboldcpp Tiefighter
🐶Tinyllama Chat
📚Stable LM 2 Zephyr 1.6b
⚡MoE LLaVA
🚀Chat with DeepSeek Coder 7B
🐬Llama 2 13b Chat
🦙LLaVA
🔥Video LLaVA
📚Llava
🏢LLaVA 1.6
👁Gradio Notebook Local Model
🐠Blind Chat
📚Web-LLM: Mistral 7B OpenOrca
🌊7B text-generation model running directly from the browser
[NSFW] C0ffee's Erotic Story Generator 2
🍑Whisper Chess
📉Play chess using voice commands
LLaMA Board
🦙Fine-tuning large language model with Gradio UI
Ratchet + Phi Locally
📕Run Phi-3 in Browser
Ratchet + Whisper Locally
🗣Run Whisper in Browser
- 4
Noosphere Webui on Cpu
🔮Clone and set up stable-diffusion-webui and extensions
- 18
epicPhotoGASM Webui on Cpu
👌Set up a stable-diffusion-webui with extensions and models
Experimental Phi3 Webgpu
🐠NeverSleep/Llama-3-Lumimaid-8B-v0.1
Text Generation • Updated • 559 • 84gradientai/Llama-3-8B-Instruct-Gradient-4194k
Text Generation • Updated • 184 • 70tiiuae/falcon-11B
Text Generation • Updated • 27.5k • 212- 14
Text-Streaming
🌘text streaming space using Gemma-7B
GemmaOnDevice
🌐Generate responses using LLM on-device
- 4.33k
OpenGPT 4o
🔥GPT 4o like bot.
PaliGemma Demo
🤲Phi-3 WebGPU
🚀A private and powerful AI that runs locally in your browser
- 1
Mistral-7B-v0.3 Fast Chat
🏃Fast chatting with Mistral v0.3
YOLOv10 Web
🌐Detect objects in uploaded images
WebGPU Nomic Embed
🏆Classify images in real-time using zero-shot classification
WebGPU Chat Qwen2
🚀Generate text using Qwen2 model
- 1
GLiNER HandyLab
⚡ Kosmos 2
💻- 7
Text Gen Playground
💫Chat with any model on the Hub
Gemini Nano (Chrome Built-in)
🚀Run Gemini Nano locally in your browser with Transformers.js
- 2
LLaVA WebGPU
🌋A private and powerful multimodal AI chatbot that runs local
Candle T5 Generation Wasm
🕯Generate text using various T5 models
- 61
MInference
🌍Generate text responses to user queries
SmolLM 360M Instruct WebGPU
🚀A blazingly fast and powerful AI chatbot that runs locally.
- 8
SmolLM 135M Instruct WebGPU
🚀A blazingly fast and powerful AI chatbot that runs locally.
- 78
Chameleon 30b
🔥Generate descriptions for images using text prompts
- 5
Nymbot Lite
✨Vision Chatbot with ImgGen & Web Search - Runs on CPU
- 3
Llama-3.1-8B-Instruct
🦙The best 8B model with 128K context
ollama-Chat
🌖Chat with Ollama
- 4
Llama CSV Agent
🤔Need to analyze data? Let a Llama-3.1 agent do it for you!
- 1
MagicPrompt Stable Diffusion
😻 WebLLM JSON Playground
🏃Generate JSON output from prompts using LLMs
Webllm Simple Chat
💬Chat with an AI assistant directly in your browser
- 79
Gemma 2 2B IT
😻Chatbot
- 1
Cohere Command R+ inference
✨c4ai-command-r-plus (hub inference, not API)
Phi-3-Mini-4k-Instruct
🐁Phi-3-Mini on hub inference
- 1
Yi-1.5-34B-Chat
🐼Yi-1.5-34B on hub inference
- 1
Mistral-7B-Instruct-v0.3
✨SOTA Small Model by Mistral AI
- 65
Falcon Mamba Playground
🐍Generate chat responses using FalconMamba-7b model
MiniCPM-V-2 6
💬Instant SmolLM
🤏Run SmolLM-360M-Instruct in realtime with MLC WebLLM
- 162
LongWriter
💬LLM for long context
- 15
Phi-3.5-Mini-Instruct
🐭New SOTA small model from Microsoft, and multilingual!
- 6
Inference Playground
🤗One-stop-shop for frequently used models
- 235
HF's Missing Inference Widget
💻Generate text responses using different models
1-Shot LLM Playground
💻Single-shot inference for rapid model testing
- 1
Phi-3.5-Mini WebLLM
⚡Engage in fast, local chat using WebLLM
- 219
Phi 3.5 Vision
🔥Generate text from an image and question
Qwen2-VL-2B
🤩Multilingual, Multimodal, Mighty 2B
Kotaemon
🚀Dataset Rewriter
🏃- 6
Reflection 70B llama.cpp
🐢Reflection-70B by Matt Schumer
- 3
Joy Caption Alpha One
⚡ Llama-3.2-3B-Instruct
🦙New SOTA small model from Meta
- 4
Llama-3.2-1B-Instruct
🦙the new tiny king
- 5
HTML To Markdown
📊Convert HTML to Markdown with readerlm-1.5B
- 387
Llama-Vision-11B
🚀Chat about images by uploading them and typing questions
Qwen-2.5 WebLLM
⚡Chat with a local language model in your browser
- 2
Llama-3.2 WebLLM
🦙Chat with a language model directly in your browser
- 109
Molmo 7B D 0924
👁 Emu3
🌖Llama 3.2 WebGPU
🦙A powerful AI chatbot that runs locally in your browser
- 3
WebLLM Playground
🏎 - 9
Nemotron-Mini
🐠NemoAligner Synthetic SFT with function calling
Zamba2 7B
🚀MiniSearch
👌Minimalist web-searching app with browser-based AI assistant
Janus Space Clone Me First
🌍Generate images from text prompts
Qwen 2.5 Code Interpreter
🐍Execute code snippets and get results
- 301
Aya Models
🌍Interact with the Aya family of models.
Wllama
🦙Run GGUF directly on your browser!
- 15
SmolLM2-1.7B-Instruct Serverless
🤏New SOTA smol king by Hugging Face
BitNet.cpp
💻- 206
JanusFlow 1.3B
🏃Huggingface space for JanusFlow-1.3B
JanusFlow 1.3B
🏃Text Gen | Vision | Image Gen | One 1.3b model
- 2
Ai Scraper
📉Scrape and summarize web content using AI
SmolVLM
📊Janus 1.3B WebGPU
🏛In-browser unified multimodal understanding and generation.
Omnivlm Dpo Demo
👁Github Issue Generator
🧑Generate structured GitHub issues
- 218
ShowUI
💻Generate clickable coordinates on a screenshot
Text-to-Speech WebGPU
🗣WebGPU text-to-Speech powered by OuteTTS and Transformers.js
- 12
Falcon3 Mamba 7b Instruct Playground
🐍Chat with Falcon3-Mamba-7B-Instruct AI assistant
- 34
Falcon3 Demo
🦅F3-DEMO
SmallThinker Demo
💬Llama 3.2 Reasoning WebGPU
🧠Small and powerful reasoning LLM that runs in your browser
DeepSeek-R1 WebGPU
🧠Next-generation reasoning model that runs locally in-browser
SmolVLM 500M Instruct WebGPU
💻Find text in images quickly
- 1
SmolVLM 256M Instruct WebGPU
🐨Upload images to generate image captions
- 3
SmolVLM
📊Generate text descriptions from images and queries
Markdown Studio
⚡Convert HTML to Markdown/JSON, Markdown Live Preview
- 1.9k
Chat With Janus-Pro-7B
🌍A unified multimodal understanding and generation model.