Needle 2
Cactus-Compute · Kit
A 45M-parameter open model for tool calling, device use and structured extraction, packed into one 14 MB binary that runs in about 28 MB of RAM. For developers…
New
AI projects from Hugging Face
Categories and filters
Listings
Needle 3
Cactus-Compute · Kit
A small on-device model from Cactus Compute for tool calling, structured extraction and text embeddings, used through the cactus Python package. For developers…
New
Whistle
Cactus-Compute · Kit
Transcribes speech in seven languages with word timestamps and speech embeddings, in a model only 16.9 MB in size. Runs from a short Python script, for develop…
New
Pluto 124M Chat
xxparthparekhxx · Kit
A small chat model that runs entirely in your browser through onnxruntime-web, on WebGPU or WebAssembly, with no server doing the inference. For people who wan…
New
Wasm Agents Blueprint
mozilla-ai · Kit
A static web page from mozilla-ai for testing AI agents powered by WebAssembly, naming the Devstral-Small-2507 and Qwen3-8B models. It suits developers explori…
New
Leokani-tts 7M
milliwattlabs · Kit
Speaks any line you type with a tiny 7M text-to-speech model that runs on your own CPU in the browser, for people who want local voice output.
New
Matcha-TTS-PL v2
machinekind · Kit
Speaks Polish text aloud in your browser with two synthetic voices. The ONNX models run on your own device with WebGPU or WebAssembly, and nothing is sent to a…
New
SADIK AI
SadikNawazAI · Kit
A multilingual chat assistant that runs fully inside your browser through WebAssembly, so your messages stay on your device. Also reachable through Ollama and…
New
Talking Pixel
cfahlgren1 · Kit
Gives you a pixel character that speaks whatever text you type, using a tiny 1.4M-parameter voice model that runs entirely in your browser with no server and n…
New