AI skills and agents for developers

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…

Idol Turbo by speridlabs

speridlabs · Kit

Turns one picture of an object into up to a million 3D Gaussians in 5 guidance-free steps, as a distilled and faster version of Idol. For 3D artists and ComfyU…

Qwen3.8-27B Turbo Brilliance NEO MAX MTP GGUF

DavidAU · Kit

Runs Qwen3.8-27B in GGUF form with a set of reasoning and instruct modes you switch from your prompt. For people who run local models and like to tune how the…

Qwen3.5-4B

Qwen · Kit

Handles text and image input with a 4B hybrid model that supports 201 languages and dialects and a 262,144-token context. For developers running small open wei…

Muse Glimmer 30B

meta-models · Kit

Reads text and images and carries out agent tasks such as tool calls and multi-step reasoning on a local machine, in a 30B model distilled from Muse Spark. For…

Raon-1 nano (GGUF)

KRAFTON · Kit

Packages the Raon-1 nano language model as GGUF files for llama.cpp, so developers can run a Korean and English chat model on their own computer. Four quant ty…

WeVisOne-VL

Comfy-Org · Kit

Packs Tencent's WeVisOne-VL model files for ComfyUI, in 4B and 2B sizes with BF16 and int8 versions. For ComfyUI users who need the files in their text encoder…

mammoth-1

baselabs · Kit

Answers a set of questions about a situation in one pass and returns a calibrated probability for each option. A 27B decision model from Base Labs at Baseten,…

Ripple-65B-Preview-GGUF

AtomicChat · Kit

GGUF quantized files of the 65B Ripple Preview agentic-coding model, for running locally with llama.cpp. For people who run large open models on their own hard…

Xiaomi-OCR-0

xiaomi-research · Kit

Parses documents and answers questions about text in images with one 0.8B OCR model from Xiaomi, covering tables, formulas and handwriting. For developers buil…

all-MiniLM-L6-v2

sentence-transformers · Kit

Turns sentences and short paragraphs into 384-dimensional vectors for semantic search, clustering and sentence similarity. For developers building English sear…

MOSS-Image-Base

OpenMOSS-Team · Kit

Draws images from text with a 5.1B text-to-image model that takes plain prompts, tag sequences or JSON layouts to place text and objects. For developers and de…

Kromoss

lodestones · Kit

Generates images from text with a full fine-tune of MOSS-Image-Base at 1024 px, plus two 8-step turbo LoRAs. A drop-in replacement for MOSS-Image-SFT, for diff…

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…

ARC 1.0

rayline-ai · Kit

Reads an agent's conversation and predicts which model will succeed, how many tokens it will use and how much reasoning to spend, so apps can route requests by…

moss_image_base_dmd2

data-archetype · Kit

Makes images from text in 8 steps instead of 50, as a distilled LoRA for the MOSS-Image-Base model. For ComfyUI and Diffusers users who want faster image gener…

Alpie Seed 9B

169Pi · Kit

Reads text, images and video and handles reasoning and coding with a 9B open-weight model built on Qwen3.5-9B, with GGUF builds for light hardware. For develop…

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…

Oc-e-Non-v1

p-e-w · Kit

Answers in about half the words of the Qwen3-4B-Instruct-2507 model it comes from, so replies are short and direct. For people who want brief text generation o…

Wan2.2-TI2V-5B

Wan-AI · Kit

Generates 720P video at 24 fps from text, or from an image plus text, and runs on a single consumer graphics card such as the 4090. A 5B video model from Wan-A…

Z-Image-Turbo

Tongyi-MAI · Kit

Generates photorealistic images from text in 8 function evaluations, with English and Chinese text rendering. For people who want fast image generation on a 16…

Qwen3.6-35B-A3B

Qwen · Kit

Helps with coding, repository-level reasoning and image-plus-text input using a 35B mixture-of-experts model that activates 3B parameters. For developers runni…

HairDeck

hyz317 · Kit

Turns one character image into stylized 3D hair cards with colors and spring-bone chains for animation, exported as GLB meshes or a VRM avatar. For avatar make…

Qwen3.8-27B GGUF (ShapeLearn Quantized)

byteshape · Kit

Runs Qwen3.8-27B as GGUF files quantized by ByteShape's ShapeLearn, in five GPU-sized options with vision input and MTP speculative decoding in llama.cpp. For…

Thinklite-27B

Sparset · Kit

A Qwen3.8-27B variant that reasons with far fewer tokens, so final answers arrive about twice as fast at high effort. For people who run reasoning models and w…

Qwen3.5-9B

Qwen · Kit

A 9B open model from Qwen that reads text and images and writes text, with a long context and support for 201 languages and dialects. For developers who want a…

Spark-X2.6-4B

XHToken · Kit

A 4.1B language model for coding, agent work and long context in English and Chinese, with three thinking levels. For developers building agents that run on th…

VoxCPM2

openbmb · Kit

Speaks text in 30 languages and nine Chinese dialects at 48 kHz, designs a new voice from a written description and clones a voice from a short clip. An open 2…

MOSS-Image-SFT

OpenMOSS-Team · Kit

A text-to-image model from OpenMOSS, fine-tuned from MOSS-Image-Base, that reads plain prompts, tags or JSON layouts to place text and objects. For people who…

DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF

ISTA-DASLab · Kit

GGUF versions of DeepSeek-V4.1-Flash-1017 at three small sizes, with each tensor quantized at its own precision. For people running a huge mixture-of-experts m…

DeepSeek-V4.1-Flash-1017-GGUF

unsloth · Kit

Unsloth's GGUF quantizations of DeepSeek-V4.1-Flash-1017, a huge image-and-text model, for running locally on a machine with 128 GB or more of RAM. For people…

Ornith-1.5-9B-GGUF

ornith-ai · Kit

Offers GGUF files of Ornith-1.5-9B, a 9B dense model trained through a self-improvement loop, for single-GPU use. Aimed at developers who want a small model wi…

Nanbeige4.3-33B

Nanbeige · Kit

A 33.1B open model for agentic coding and professional cowork tasks, built as the flagship teacher of the Nanbeige4.3 series. For developers and agent builders…

Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF

ISTA-DASLab · Kit

A coding-focused GGUF build of Qwen3.8-Flash-Next with half its experts removed, cutting 354 GB at BF16 to 58.4 GB while keeping image input. For people with l…

NVIDIA NemotronLabs RE-USE

nvidia · Kit

Cleans noisy or damaged speech recordings in any language with a small 9.6M-parameter model from NVIDIA. For audio and speech developers who need clearer voice…

Mage-VL-Cowork

microsoft · Kit

Operates a computer from screenshots and terminal commands with one small vision-language model of about 4B parameters, made by Microsoft for people who build…

Idol by Comfy-Org

Comfy-Org · Kit

Turns an image into a 3D Gaussian splat inside ComfyUI, using repackaged files of a TripoSplat fine-tune. For people who build 3D results from pictures in Comf…

Recursive Flint

RecursiveSI · Kit

A 39.8B mixture-of-experts language model for coding agents that investigates codebases, fixes bugs, adds features and writes tests. For developers who run the…

Alpamayo 2 Edge

nvidia · Kit

Reads multi-camera driving footage, a navigation instruction and motion history, then outputs a driving trajectory with a written reason, and answers questions…

gemma-4-31B-it

google · Kit

An instruction-tuned 31B model from Google DeepMind that reads text and images and writes text, with a 256K context and configurable thinking. For developers w…

dale-0.8b-GGUF

manuelgscom · Kit

A small 4-bit GGUF model that turns a plain request in Spanish or English into one Linux bash command. It runs offline on a CPU inside the dale tool. For peopl…

Qwen3.8-27B-DSpine-b16-GGUF

aj9o9 · Kit

A GGUF draft model that speeds up Qwen3.8-27B in llama.cpp through speculative decoding, reaching about 125 tokens per second on code and math on one RTX 3090.…

Kokoro-82M

hexgrad · Kit

Turns text into speech with a small open-weight model of 82 million parameters, with 54 voices in version 1.0. For developers who want fast, low-cost speech in…

MOSS-Image-heal by KBlueLeaf

KBlueLeaf · Kit

A fine-tune of the MOSS-Image-Base text to image model by KBlueLeaf that shrinks the huge values in its internal stream while keeping outputs close to the base…

Qwen3.8-Flash-Next-GSQ-RCO-GGUF

ISTA-DASLab · Kit

GGUF versions of Qwen3.8-Flash-Next at four sizes, with each tensor quantized at its own precision and a vision projector for image input. For people running a…

MOSS-Image

Comfy-Org · Kit

Text-to-image and image-edit model files for ComfyUI, repackaged from the OpenMOSS MOSS-Image family. For ComfyUI users who generate or edit pictures in node w…

Laya

convaiinnovations · Kit

Answers typed questions about a message, email, ticket or JSON record with calibrated probabilities in one pass of about 33 ms, in 100+ languages. For develope…

DeepSeek-V4.1-Flash-1017-GSQ-RCO-Coder-GGUF

ISTA-DASLab · Kit

An expert pruned and quantized GGUF of DeepSeek-V4.1-Flash-1017 from ISTA-DASLab, aimed at code and agent work, with transformer weights of 72.1 GB. Suits deve…

THX-02 by HAL-X-AI

HAL-X-AI · Kit

Answers plain-language questions about a message, document, image or chart with a probability for every option, in tens of milliseconds. For developers who rou…

Qwenx86-4B (compact)

Quazim0t0 · Kit

Runs a calculator, Python and a C compiler inside its own weights, using 13 extra layers placed ahead of Qwen3.5-4B. For researchers and tinkerers who study mo…

Unlimited-OCR

baidu · Kit

Parses document images and multi-page PDFs into text with a 3.3B vision-language model from Baidu. For developers who add OCR and document parsing to their own…

AREX-2

BAAI · Kit

Improves its own solutions over several rounds of propose, measure, reflect and revise, using a 27B model from BAAI. For agent researchers and developers worki…

Nex-N2.6

nex-agi · Kit

Handles computer use, coding and long tool-driven tasks as a multimodal agentic model built on GLM-5.3-Flash, in FP8 weights of about 321B parameters. For team…

KLM 1.6

MinimaLabs · Kit

Continues English text with a tiny 99M base language model from MinimaLabs. For researchers and hobbyists who want a small model to study, test or fine-tune.

Unlimited-OCR-2

baidu · Kit

Baidu's 3.3B document parsing model for long documents, using SR-SWA attention to keep decoding cost nearly flat, with Transformers and SGLang routes. Suits te…

GLM-5.3-Flash

zai-org · Kit

zai-org's natively multimodal GLM-5 series model with 320B total and 18B active parameters, with a hybrid sparse and linear attention design and a thinking bud…

DeepSeek-V4.1-Flash

deepseek-ai · Kit

DeepSeek's multimodal mixture of experts model with a 552B backbone and a one million token context, built to cut KV cache cost for long input agent work. Suit…

Mithi v1 Flash

Oomni · Kit

Reads text aloud in 11 Indian languages with a male and a female voice, on a GPU or a plain CPU. Made for developers who add speech to apps.

S5-nano

maritaca-ai · Kit

Maritaca AI's small Portuguese and English model built on Qwen3.5-4B, with Think and Instruct modes and strong tool use, in BF16 for vLLM and SGLang. Suits dev…

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…

Qwen3.8-27B-GSQ-RCO-GGUF

ISTA-DASLab · Kit

ISTA-DASLab's GGUF versions of Qwen3.8-27B in four sizes, each tensor quantized at its own precision, with a vision projector for images. Suits people who run…

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…

embeddinggemma-2

google · Kit

Google DeepMind's open embedding model that places text, code, images, video and audio in one 768 number vector space, built to run on laptops and phones. Suit…

LongCat-2.5

meituan-longcat · Kit

Meituan LongCat's multimodal mixture of experts model for long agent tasks and coding, with about 1.6 trillion total parameters and 48 billion active per token…

TorchCAM

frgfm · Kit

A Docker app from frgfm for class activation maps on PyTorch models, such as CAM and Grad-CAM, which show where an image model looked. For developers who want…

Holocron

frgfm · Kit

A Gradio demo from frgfm for Holocron, a collection of recent computer vision techniques written in PyTorch, using the rexnet1_0x model. For people who want to…

Generative_python_transformer

equ1 · Kit

A Gradio app from equ1 that, going by its name, generates Python code with a transformer model whose weights and tokenizer files sit in its repository. For dev…

Lama Example

CVPR · Kit

A Gradio app from the CVPR organisation with a large code base and sample images that point to filling in masked parts of a picture. Its README gives no descri…

GFPGAN Example

CVPR · Kit

A Gradio app from the CVPR organisation that carries the full GFPGAN face restoration code, built to try in a browser. Its README gives no description, so the…

Anime Image Labeller

curt-tigges · Kit

A Gradio app that puts labels on anime pictures with trained model files, a label list and notebooks in its repository. It suits people who want to try image l…

Harry Potter Q A

cpnepo · Kit

A Streamlit app for asking questions about a text file, pairing a search model with an answer model. Its name points to Harry Potter. It suits fans and develop…

Landmark Detection

coolzude · Kit

A Gradio app whose name points to landmark detection, built to try in a browser. Its README gives no description, so the page shows what it takes and returns.

Clasificador_de_mascotas

cabustillo13 · Kit

A Gradio app, the name meaning pet classifier in Spanish, that runs a saved model on pet photos, with three sample photos. It suits people who want to try a sm…

CnOCR Demo

breezedeus · Kit

A Gradio demo of CnOCR, a Python OCR toolkit that reads English, numbers, Chinese and vertical text from pictures. It suits people who want to try it before in…

Projected GAN

autonomousvision · Kit

A Gradio app that wraps a GAN image generator from the autonomousvision group, built to try in a browser. Its README gives no description, so the page shows wh…

Uohproject

aturate · Kit

A Gradio app that ships a saved model file and a second binary file, built to try in a browser. Its README gives no description, so the page shows what it take…

ASR Ukrainian

arampacha · Kit

A Gradio app that turns spoken Ukrainian into text with a wav2vec2 XLS-R checkpoint. It suits people who want to transcribe Ukrainian audio in a browser.

Practica1

AP2122 · Kit

A Gradio app that runs a saved model on pictures, with two sample pictures of buildings and a forest. It suits people who want to try a small image model in a…

Hindi_ASR

anuragshas · Kit

A Gradio app that turns spoken Hindi into text with the anuragshas wav2vec2 XLS-R model. It suits people who want to transcribe Hindi audio in a browser.

Uniformer_video_demo

Andy1621 · Kit

A Gradio demo that labels short videos with the Andy1621/uniformer model, with three sample clips. It suits people who want to try video classification in a br…

Uniformer_image_demo

Andy1621 · Kit

A Gradio demo that classifies pictures with the Andy1621/uniformer model, with four sample pictures. It suits people who want to try image classification in a…

Sentiment_analysis

anbohan · Kit

A Gradio app that, going by its name, judges the sentiment of text. No model is named and the README gives no steps, so the page shows what it returns.

Sharktankind Analysis

Amrrs · Kit

A static web page titled as an analysis, made of plain HTML and CSS and run in the browser with nothing to install. Its README does not say what it analyses.

Image Caption With Vit Gpt2

Amrrs · Kit

A Gradio app that writes a short caption for a picture, pairing a vision transformer with a GPT-2 style text model. It suits people who want to try image capti…

Duygu_Analizi

alperbayram · Kit

A Gradio app for sentiment analysis of Turkish text using the savasy/bert-base-turkish-sentiment-cased model. It suits people who want to check the tone of Tur…

GFPGAN

akhaliq · Kit

A Gradio app named after the GFPGAN face restoration approach, built to try in a browser. Its README gives no description, so the page shows what it takes and…

Self Supervised Ner PER ORG LOC

ajitrajasekharan · Kit

A Streamlit app for tagging people, organizations and locations in text, with an ensemble config in its repository. It suits people who want to try entity tagg…

Self Supervised Ner Biomedical

ajitrajasekharan · Kit

A Streamlit app for named entity recognition in biomedical text, with an ensemble config and batch scripts in its repository. It suits people who want to try e…

Qualitative Pretrained Model Evaluation

ajitrajasekharan · Kit

A Streamlit app for comparing pretrained language models by eye. It names six models, from scientific, biomedical and legal ones to general BERT, and suits peo…

NER Biomedical PHI Ensemble

ajitrajasekharan · Kit

A Streamlit app for named entity recognition in biomedical text that combines three named models through an ensemble config. It suits people who want to try en…

Image Text Detection

ajitrajasekharan · Kit

A Streamlit app that reads handwritten text from a picture with the microsoft TrOCR handwriting models. It suits people who want to try handwriting recognition…

BiomedicalNERModel

ajitrajasekharan · Kit

A Gradio demo for named entity recognition in biomedical text, built around the ajitrajasekharan/biomedical model. It suits people who want to try entity taggi…

Pytorch Image Classifier by abidlabs

abidlabs · Kit

A Gradio 3.0.17 image classifier demo with two sample photos, a cheetah and a lion. It suits people who want to try image classification in a browser.

Pytorch Image Classifier

abidlabs · Kit

A Gradio image classifier demo with four sample photos, a banana, a car, a cheetah and a lion. It suits people who want to try image classification in a browse…

Draw2

abidlabs · Kit

A Gradio app that bundles its own PyTorch model file and a list of class names, built to try in a browser. Its README gives no description, so the page shows w…

Chatbot Minimal by abidlabs

abidlabs · Kit

A short Gradio chatbot that answers with the microsoft/DialoGPT-medium model. It suits people who want to try a small chat page or read a compact example of on…

Chatbot Minimal

abidlabs · Kit

A short Gradio chatbot that answers with the microsoft/DialoGPT-medium model. It suits people who want to try a basic chat page or read a small example of one.

Wikipedia Protection

abhi12ravi · Kit

A Gradio app whose title points to Wikipedia page protection, with a saved model file and a helper module. It suits people who want to try it in a browser or r…

Gradio Demo

Abdoulayegk · Kit

A small Gradio app you can try in the browser or run on your own computer with Python. Its README gives no description, so you learn what it does by opening it.

Multi-Agent AI - Coding

bstraehle · Kit

A Gradio demo of several AI agents built with Microsoft AutoGen that work together on a coding task. Use it in the browser on Hugging Face or run a copy on you…