AI projects from Hugging Face

gemma-4-26B-A4B-it Cactus CQ

Cactus-Compute · Kit

2-bit, 3-bit and 4-bit compressed copies of Google's gemma-4-26B-A4B-it chat model in the Cactus weights format. Built to run on ARM devices through the Cactus…

Spark-X2.6-4B-FP8

XHToken · Kit

Compact 4.1B-parameter text model in FP8 form for on-device use, with three thinking levels (none, low, high) and English and Chinese support. Aimed at coding…

Spark-X2.6-1.7B-Base

XHToken · Kit

A compact 1.7B language model for on-device use in English and Chinese, with gains in coding, agent tasks and long context, and three adjustable thinking level…

Indic Tiny TTS: Hindi

sulabhkatiyar · Kit

Reads Hindi text in Devanagari script aloud with a female or a male voice, small enough to run on a CPU without a GPU. Made for developers adding Hindi speech…

Chatterbox-Nano

ResembleAI · Kit

Speaks English text aloud on a plain CPU with a 110M-parameter model, and adds laughs and coughs through tags in the text. Suits developers who need fast on-de…

Gemma 4 12B IT (LiteRT-LM)

litert-community · Kit

Runs Gemma 4 12B on your own desktop with text, image and audio input, no internet needed. A LiteRT-LM build for developers who want private, on-device generat…

Granite-4.0-H-350M

ibm-granite · Kit

Handles summaries, classification, extraction, question answering, RAG, code tasks and tool calling in 12 languages with a 340M-parameter instruct model from I…

SmolVLM2-2.2B-Instruct

HuggingFaceTB · Kit

Answers questions about videos, images and text together, with a 2.2B model that needs about 5.2 GB of GPU memory for video. For developers building visual ass…

Maple-Preview

deepgrove · Kit

A 20B ternary-weight reasoning model that activates about 1B parameters per token. Built for fast on-device use, with a 5.31 GB checkpoint and 131,072 token co…

MiniCPM5-2B-GGUF by bartowski

bartowski · Kit

Quantized GGUF copies of the MiniCPM5-2B text model in many sizes, made with llama.cpp and an importance matrix. For people running a small English and Chinese…

SmolLM2-360M

HuggingFaceTB · Kit

Continues English text from a prompt with a 362M-parameter base language model trained on 4 trillion tokens and light enough for on-device use. For developers…

Smaug-Decisions

abacusai · Kit

Answers a typed question about audio, an image or text with a probability for each option, in one pass and with no generated text. A 4B decision model fine-tun…

Zabibu Fikra Model 2 (4B)

zabibutechnika · Kit

Answers in Swahili and English from a 4B model made to run privately on your own device, offline. Suits on-device assistants that need African context, such as…

MNN-Pocket-0.3B-Base

taobao-mnn · Kit

A pre-trained base language model of about 300M parameters for Chinese and English, designed with the MNN inference engine for on-device use, as a start for fu…

1-bit Bonsai 27B (MLX)

prism-ml · Kit

Runs a 27B-class reasoning model packed to 1 bit per weight, about 3.9 GB, on Apple MLX, with 262K-token context. For developers who want a large model on a ph…

Bonsai-1.7B-GGUF

prism-ml · Kit

Generates text with a 1.7B language model packed to 1 bit per weight, about 0.24 GB, for llama.cpp on CUDA, Metal and CPU. For developers who need a tiny local…

Gemma 4 E4B IT (LiteRT-LM)

litert-community · Kit

Runs a small Gemma 4 model on phones, desktops, IoT boards and the web without an internet connection. A 3.66 GB LiteRT-LM build for developers who want privat…

Spark-X2.6-4B-AgentFast

JamieBradfield · Kit

Calls tools and follows instructions with almost no thinking delay, as a 4.1B fine-tune of Spark-X2.6-4B. Made for people building fast local agents that need…

SmolLM2-135M

HuggingFaceTB · Kit

Continues English text from a prompt with a 135M-parameter base language model small enough to run on-device. For developers who want a tiny model to test idea…

POCKET-35B-GGUF

FINAL-Bench · Kit

Runs a Korean-tuned 35B model on your own PC from GGUF files with llama.cpp, with a CPU-only path so no GPU is needed. For people who want a local language mod…

Phonon-2.5 English

FermionResearch · Kit

Transcribes English speech to text in a 157.6 MB download that runs on Apple silicon, Linux and Windows CPUs without a GPU. It suits teams doing dictation, cap…

MNN-Pocket-0.3B-MNN

taobao-mnn · Kit

Runs a 0.3B Chinese and English chat model on phones and edge devices through the MNN runtime, as a 4-bit build of about 173 MB. For developers adding on-devic…

MNN-Pocket-0.3B-Dec

taobao-mnn · Kit

Reads a text state plus your questions and picks one of your options for each, with a probability per candidate, in a single pass. A decision model for develop…

SmolLM2-135M-Instruct

HuggingFaceTB · Kit

Answers chat-style questions and handles rewriting and summaries with a 135M-parameter instruction-tuned model small enough for on-device use. For developers w…

SmolLM2-1.7B-Instruct

HuggingFaceTB · Kit

Chats, rewrites and summarizes text and can call functions, in a compact 1.7B model small enough to run on-device. The instruction-tuned SmolLM2 from HuggingFa…

Phonon-2.5

FermionResearch · Kit

Transcribes speech in 25 languages with a 156.2 MB model that needs no graphics card. An open model from FermionResearch for Apple silicon Macs and ordinary Li…

Spark-X2.6-4B-Base

XHToken · Kit

A 4.1B language model for on-device use, tuned for coding, agent tasks, long context and reasoning in English and Chinese, with three thinking levels. For deve…

MiniCPM5-2B-GGUF

openbmb · Kit

Gives you MiniCPM5-2B, a small dense text model for English and Chinese, as GGUF files for on-device and local use. Suits people who want a compact model for c…

Idol on LiteRT

litert-community · Kit

Turns one photo of an object into a 3D Gaussian splat on an Android phone, using LiteRT versions of the Idol model and a sample app, for mobile and 3D develope…

embeddinggemma-2-740m-litert-lm

litert-community · Kit

The 740M multimodal EmbeddingGemma 2 packaged for on-device use with LiteRT-LM. It maps text, code, images, video and audio into one shared 768-dimensional vec…

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…

Supertonic 3

Supertone · Kit

Turns text into speech in 31 languages, running on your own device through ONNX Runtime with no cloud call. For developers who want fast local voice output wit…

Bonsai-27B-gguf

prism-ml · Kit

Runs a 27B-class reasoning model as a 1-bit GGUF file of about 3.9 GB for llama.cpp, so it fits a laptop or one GPU. For people who want local reasoning on eve…

Laplace-1-Vector by JuneoAI

JuneoAI · Kit

Judges which action an AI agent should take, who should own a task and who may see what, as a 4B model that runs on your own hardware so organizational data st…

CherryPit-1.2-2B

DRUPEs · Kit

A 2B coding and chat model built on MiniCPM5-2B that is much better at web apps needing several features in one component. For developers who want a small loca…

Silencio-2

BlueRoseLabs · Kit

Turns English text into 24 kHz speech with emotion and sound tags, and can copy a voice from a short reference clip. A tiny text to speech model fine-tuned fro…

Spark-X2.6-1.7B

XHToken · Kit

Generates text with a compact 1.7B model for on-device use, with three adjustable thinking levels. Suits developers who want coding, agent and long-context hel…

embeddinggemma-2-GGUF

unsloth · Kit

Turns text into 768-dimensional vectors for on-device search, retrieval and clustering. The base model also covers images, video and audio. Packaged as GGUF by…

Klein-TTS-X1.5-Pro

klein-ml · Kit

Turns text into 24 kHz speech in four languages with a 13.1M parameter model and 17 voices that run faster than real time on a CPU. For developers who need a s…

Underdog Bark 3.0

ConwayResearch · Kit

Turns English speech into text with a 0.6B model in a 163 MB download, built on NVIDIA's Parakeet TDT 0.6B v3. For developers and Apple-silicon users who want…

Spark-X2.6-1.7B-GGUF

XHToken · Kit

Runs a small 1.7B on-device language model from XHToken as 4-bit GGUF files, for chat, coding and agent tasks in English and Chinese, with adjustable thinking…

gemma-4-E2B-it-litert-lm

litert-community · Kit

Gemma 4 E2B instruction-tuned model packaged as a .litertlm file for the LiteRT-LM framework, made for private on-device use on phones, desktops and edge devic…

jevos-v4

feder-cr · Kit

A local decision model that answers yes-or-no, multiple-choice and score questions about a text on a laptop CPU in about 28 to 130 ms, returning a probability…

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…

MiniCPM5-2B

openbmb · Kit

Generates text with a dense 2B-class model made for on-device and local use, covering coding, math, long context, tool use and agent tasks in English and Chine…

BotPsy-0.8B

qvac · Kit

A small 0.8B model for function calling and agent workflows, built on Qwen3.5-0.8B and light enough to run on a device, for developers who want a local assista…

Spark-X2.6-4B-GGUF

XHToken · Kit

A compact 4B language model in GGUF form for on-device use, tuned for coding, agents and long context, with three thinking levels from none to high. Works in E…

MNN-Pocket-0.3B-GGUF

taobao-mnn · Kit

Runs a compact 0.3B Chinese and English language model from GGUF files of 192 to 726 MB, made for phones, laptops and other on-device use with llama.cpp, LM St…

BotPsy-0.8B-GGUFs

qvac · Kit

GGUF copies of the 0.8B BotPsy tool-calling model in BF16, Q8_0 and Q4_K_M, for running agent and function-calling work fully on your own device with llama.cpp.

phonon-31m-en

gradium · Kit

A small English text-to-speech model that streams natural 24 kHz audio and runs on a laptop CPU, a phone or in a browser tab. For developers who want speech on…

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…

Cactus runtime

Cactus-Compute · Kit

Provides prebuilt runtime binaries that run text, speech and vision models locally on phones, laptops, servers and browsers. For developers who ship on-device…

Mach Boom

SyzygyResearch · Kit

Turns English text into speech on a single CPU core, using a 3.5-bit version of Gradium's Phonon 31m model that runs several times faster than real time, for d…

Earlybird by sahilmahendrakar

sahilmahendrakar · Kit

Turns speech into text on a device and predicts each word before the speaker finishes it, scoring every word. A 16.8 MB English model for voice agents and live…

Raon-1 nano

KRAFTON · Kit

Generates text and follows instructions in Korean and English, keeps conversation context and calls tools. A 3.1B-parameter language model with a 262,144-token…

MNN-Pocket-0.3B

taobao-mnn · Kit

A small English and Chinese instruction tuned language model of about 300M parameters, designed with the MNN stack for running on phones and tablets. Suits dev…

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.

Supertonic 3 (TTS)

Supertone · Kit

A web page demo of Supertonic 3 text-to-speech that Supertone describes as fast, on-device, multilingual and accurate. Runs in your browser. Suits creators and…

LinnetTTS

VoxRT · Kit

Speaks text aloud with LinnetTTS, a small on-device text-to-speech model that streams audio and runs in real time on a CPU. For developers and anyone who wants…