AI projects from Hugging Face

Fara1.5-9B

microsoft · Kit

A computer use agent model from Microsoft Research that reads browser screenshots and picks the next click, typing or scroll to finish web tasks. It suits deve…

GLM-5.3-Flash EXL3 3.5bpw

Mia-AiLab · Kit

Quantized copy of GLM-5.3-Flash in EXL3 format, 156 GB, with narrower routed experts, about 11 percent smaller than the same lab's 4-bit version. For people ru…

Mesmer AI Detector 4B

mesmertech · Kit

Tells whether English text is human-written, AI-written or AI-edited and labels each sentence. For editors, teachers and researchers who want a signal, not pro…

LongCat-Flash-Lite-Sparse

meituan-longcat · Kit

Mixture-of-experts text model with 69B parameters, about 3B active per token, sparse attention and a 1M-token context. For teams hosting long-context models fo…

LongCat-2.5-W4A4

meituan-longcat · Kit

Multimodal mixture-of-experts model for long agentic tasks such as codebase work, full project builds and creative design, in a compressed W4A4 build. For team…

Qwen3.5-4B-Router-1M

MaziyarPanahi · Kit

Small decider that returns a calibrated probability for what an agent should do next and which tool it should call. For developers building agents and support…

Qwen3.5-4B-Judge-1M

MaziyarPanahi · Kit

Small judge model that returns a calibrated probability on whether a reply is backed by its source, whether text is unsafe, and which task or domain it belongs…

Koharu Layout HighRes

mayocream · Kit

Detects text, sound effects, speech bubbles and panels on manga pages, returning boxes and masks. For people building manga translation and cleanup tools with…

Temper-2-Nodel

maylore-ai · Kit

Rust coding model of 4.2B parameters, built on Qwen3.5-4B, that answers requests in Russian and English. For Rust developers who want a small model for functio…

SpatialLM1.1-Qwen-0.5B

manycore-research · Kit

Reads 3D point clouds and writes a structured scene layout with walls, doors, windows and labelled object boxes. For researchers and developers working on robo…

llm-jp-4.1-33b-thinking

llm-jp · Kit

A 33.2B-parameter English and Japanese text generation model from the LLM-jp project. Post-trained with SFT and DPO, it has a 65,536-token context, Apache 2.0…

SPARSEUP

Linkup-Platform · Kit

A 188M-parameter English sparse retrieval model from Linkup that turns queries and documents into weighted word lists for search. It scores 56.4 on BEIR, the b…

Pocket TTS

kyutai · Kit

A 100M-parameter text-to-speech model from Kyutai that runs on CPUs in six languages, streams audio with about 200 ms to the first chunk, and works from Python…

KAT-Coder-V2.5-Dev

Kwaipilot · Kit

An open-weight coding model from Kwaipilot, a mixture-of-experts with 35B total and 3B active parameters, tuned for agentic coding and fewer tool-call glitches…

Qwen3.8-27B-Fable-5-Coding-Distilled

khazarai · Kit

Debugs and reviews code by checking real files before it proposes a fix, a Qwen3.8-27B fine-tune trained on 195M tokens of reasoning traces. For developers who…

Slonik-27B-oQ8-mtp

kakoka · Kit

Helps write and change PostgreSQL source code with a 27B coding model, 8-bit quantized to run locally on Apple Silicon Macs through oMLX. For PostgreSQL develo…

Qwen3.8-27B-oQ6e-mtp

Jundot · Kit

A mixed-precision MLX copy of Qwen3.8-27B at about 6.9 bits per weight, with the vision encoder and multi-token prediction head included, for running locally o…

Qwen3.6-35B-A3B-oQ6e-mtp

Jundot · Kit

A mixed-precision MLX copy of Qwen3.6-35B-A3B at about 6.8 bits per weight, with the vision encoder and multi-token prediction head included, for running local…

gemma-4-E4B-it-weight-space-programming

jstarks · Kit

Google's Gemma 4 E4B-it with 0.002% of its weights edited directly, no training, to fix stalls in thinking mode with tool calls and multi-step math. Also ships…

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…

Qwopus3.8-27B-Coder-Flash

Jackrong · Kit

Writes code, calls tools and works through software tasks as a coding agent. A 27.8B fine-tune of Qwen3.8-27B by Jackrong, trained on about 200,000 code and re…

Seb-9B-v2

ironbcc · Kit

A 9B decision model based on Qwen3.5-9B. You give it a situation, a question and options, and it returns how likely each option is, in one pass with no text ge…

multilingual-e5-large

intfloat · Kit

Turns text in about 100 languages into 1024-number vectors for search, matching and retrieval. A 560M-parameter embedding model from intfloat, built on xlm-rob…

Qwen3.8-27B-DFlash2 by incoai

incoai · Kit

Speeds up Qwen3.8-27B by drafting blocks of tokens that the main model then checks, with output unchanged. A 1.9B draft model for SGLang and vLLM servers, not…

Ming-Image-0.1-Design

inclusionAI · Kit

A 6B text-to-image model from inclusionAI for interface mockups, infographics, posters and other text-heavy designs, with transparent-background (RGBA) output.

K2-Horizon-7B-Uno

IFM · Kit

A LoRA adapter that adds a diffusion pathway to IFM's K2-Horizon-7B language model, for research into faster text generation. It holds only the adapter, not th…

granite-4.2-3b

ibm-granite · Kit

Reasons step by step before it answers, with tool calling, code generation and multilingual chat, in a compact 3B model from IBM. Supports a 128K context nativ…

SmolLM2-360M-Instruct

HuggingFaceTB · Kit

Answers chat-style questions and handles rewriting and summaries with a 362M-parameter instruction-tuned model that runs on modest hardware. For developers who…

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…

Carbon-X

HuggingFaceBio · Kit

Reads raw DNA inside a chat and answers in English, judging whether variants look benign or pathogenic, for researchers who want a DNA language model on their…

Spark-X2.6-4B-Blender

hotocooo · Kit

Writes Blender 5.x Python scripts that build clean, quad-dominant meshes such as props, furniture, products and human or animal base meshes. A 4B fine-tune of…

Crystal-31B-RL

hiwaifu-research · Kit

A role-play chat model post-trained from Gemma 4 31B-IT that replies in the user's language, whether Russian, Spanish, English or Portuguese, and stays in it.…

hs-embed-1

hindsight-ai · Kit

Turns text into compact vectors for search and matching in eight languages, with inputs up to 8,192 tokens. A small 112M embedding model built for Hindsight, r…

Holo4-27B

Hcompany · Kit

Looks at screenshots and decides the next click, keystroke, code run or tool call, built on Qwen3.8-27B. A computer-use model for web, desktop and mobile agent…

LeVJEPA 1.5 Large

galilai-group · Kit

Encodes video clips and single images into feature vectors, trained by self-supervised learning on about 5,300 video hours. A video encoder for researchers, un…

bekko-static-v1-slim-100k

flowercomputers · Kit

Turns text into 1024-dimension vectors with a static embedding model, trimmed to 25 languages. Fast sentence similarity and retrieval, without a transformer, i…

GLiNER2.5 Multi

fastino · Kit

Pulls entities, labels, structured records and relations out of text with one multilingual model. A 287M-parameter extractor from fastino that runs locally on…

AuraSR-v2

fal · Kit

Upscales generated images four times with a GAN-based super-resolution model. Made for people who generate pictures and want them larger, from fal.

V-JEPA 2

facebook · Kit

Turns videos and images into embeddings for video classification, retrieval, or as the video encoder of a vision-language model. Built by FAIR at Meta for deve…

MedErtas v0.1 31B LS

ErtasAI · Kit

Serves a medical-domain language model, a compressed Gemma 4 31B, on vLLM and NVIDIA Blackwell GPUs. Built for medical AI products that need fast, low-cost ans…

KVARK Sparkle 1.1 (27B)

Egzakta · Kit

A 27B model tuned for document work: it searches a document base, answers from what it finds and says so when the answer is missing, for builders of document a…

bert-base-NER

dslim · Kit

Finds and labels people, organizations, locations and miscellaneous names in English text. A fine-tuned BERT model for named entity recognition, used through t…

Qwen3.5-4B-SFT-decompiler-O0-full

Divij · Kit

Rewrites decompiler output into readable C source with meaningful names and proper types. A Qwen3.5-4B fine-tune trained on unoptimized binaries, for security…

Qwenputer-npu

divagr1925 · Kit

A Qwen3.5-4B model with a small RISC-V computer built into its weights, used for exact arithmetic and for running a tiny story model. An experiment for researc…

Qwen3.5-4B Qwenputer Filesystem

divagr1925 · Kit

An experimental Qwen3.5-4B with a RISC-V CPU and a small filesystem compiled into its weights, so it remembers facts across sessions without outside tools. The…

DistilBERT base uncased

distilbert · Kit

A small, fast English language model distilled from BERT base, with 67M parameters. Fills in masked words and is mainly meant to be fine-tuned for classificati…

DeepSeek-V4-Pro

deepseek-ai · Kit

Generates text with a 1.6T-parameter Mixture-of-Experts model that activates 49B per token and reads up to one million tokens. A DeepSeek preview for teams tha…

DeepSeek-V3.2

deepseek-ai · Kit

A 685B open reasoning model from DeepSeek with sparse attention for long context and a chat template that lets it think while it calls tools. For teams that ru…

Hydrogen-1.0 NVFP4

deep-principle · Kit

A 4-bit NVFP4 build of Hydrogen-1.0, a 381B science and research assistant model from Deep Principle, based on GLM-5.3. It needs a multi-GPU NVIDIA Blackwell s…

Hydrogen-1.0-MXFP4

deep-principle · Kit

An MXFP4 quantized copy of Deep Principle's 384B Hydrogen-1.0 science assistant, for AMD Instinct hardware. For labs that want a text model for scientific ques…

Qwen3.8-27B-AWQ-INT4

cyankiwi · Kit

A 4-bit AWQ quantization of Qwen3.8-27B by cyankiwi, a 27B vision-language model with thinking control. Weights are 21.02 GB and load in Transformers, vLLM or…

cua-s1-forms

cua-ai · Kit

Scores the possible actions for each element of a GUI form, such as fill, check, click or skip, and returns a probability for each. A tiny model for developers…

cbx-indic-pii-extractor-17M

CobuildX-AI · Kit

Finds personal information such as names, phone numbers, Aadhaar and PAN in Indian-language and Indian English text and returns each value's position. A 16.7M-…

Nimble-v4-max

bespokelabs · Kit

Gives a probability for every answer option when you pass a context and typed questions such as choices, yes or no, or ordered scores. A fine-tune of Qwen3.8-2…

Bespoke-Nimble-9B

bespokelabs · Kit

Scores yes or no questions, multiple-choice picks and rubric levels against a piece of text, using a LoRA adapter on Qwen3.5-9B. For developers who need a clas…

NorthCUA-Nano

beipo-ai · Kit

Operates desktop and browser apps from screenshots with a 9B dense computer-use model built on Qwen3.5. Suits developers who build computer-use agents with the…

bge-small-zh-v1.5

BAAI · Kit

Turns Chinese text into dense vectors for search, classification, clustering and semantic matching. A 24M-parameter BGE embedding model from BAAI under the MIT…

safetensored-upscalers

AshtakaOOf · Kit

Image upscaling models, and a few other image-to-image ones, gathered in one repository as safetensors files converted from older pickle files. For people who…

Ling-3.1-flash-DSpark

AQ-MedAI · Kit

A small draft model that speeds up Ling-3.1-Flash with speculative decoding in SGLang, drafting 5 or 7 tokens at a time. For teams serving Ling-3.1-Flash on NV…

Molmo2-4B

allenai · Kit

Answers questions about images, videos and groups of images, and can point to what it finds. An open vision-language model from Ai2 for developers and research…

Signal 3.8 27B

agentionai · Kit

Gives shorter, more direct answers than Qwen3.8-27B by using fewer answer and thinking tokens, so replies finish sooner. A light fine-tune that drops into the…

ACE-Step 1.5 XL Turbo

ACE-Step · Kit

Generates music and other audio in just 8 steps with a 4B-parameter diffusion model, run locally through a Gradio interface. For creators and developers with a…

Smaug Humanizer

abacusai · Kit

Rewrites AI-written text in a human voice while keeping its facts, numbers, names and layout. A 12B model fine-tuned by Abacus.AI from Gemma 4, for writers and…

Jocasta-diff-VLA

RobotLearningLab · Kit

A robot control policy that adapts Dream-VLA-7B to eight simulated Panda arm task families in robosuite, using a Flow Matching action head. For robotics resear…

G4-LuneLight-31B

zerofata · Kit

Provides a 31.3B-parameter language model built on ReadyArt's gemma-4-31B-it-scotoma-2, for people who run models on their own hardware. The card text here doe…

GLM-5.3-Flash-BF16

zai-org · Kit

A 320B-parameter multimodal model with 18B active that reads text and images, with an adjustable thinking budget and a hybrid attention design for long context…

GLM-5.2

zai-org · Kit

A 753B-parameter open text model from zai-org for long, multi-step work such as coding and agent tasks, with a 1M-token context and an MIT license. For teams w…

Qwen3.8-27B-CodeForge-3xMerge

xtools-at · Kit

Writes and explains code and works through reasoning problems, from a weighted merge of three Qwen3.8-27B fine-tunes. For developers who want one general-purpo…

Wan2.1-VACE-1.3B

Wan-AI · Kit

Makes and edits video with Wan2.1's VACE model, from a prompt, a still image or an existing clip, with English and Chinese text inside videos. For video creato…

RubatoCodec

third-intelligence · Kit

Compresses speech into a fixed number of variable-length events with durations, and decodes them back as it streams. A neural speech codec for people building…

Inkling-Small-NVFP4

thinkingmachines · Kit

The NVFP4 copy of Inkling-Small, a multimodal mixture-of-experts model that takes text, images and audio and writes text. For developers building agents, codin…

Hy-MT2-30B-A3B

tencent · Kit

A 30B mixture-of-experts translation model from Tencent that translates among 33 languages and follows translation instructions. For teams that need high-volum…

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…

UltraGliClass v0.1

Srimon12 · Kit

A 154M-parameter zero-shot text classifier that scores every label you pass in one pass, for single-label, multi-label and intent tasks, including long inputs.…

Mica-v0.5-4B

sky7350 · Kit

A 4B classifier built on Qwen3.5-4B that reads an input and returns a probability for each allowed answer, for guardrails, routing, triage and agent gates. For…

Assistant_Pepe_32B

SicariusSicariiStuff · Kit

A 32.8B-parameter English model built on Qwen3-32B and released in 8B, 32B and 70B versions. The card text shows only page styling, so its exact purpose is not…

paraphrase-multilingual-MiniLM-L12-v2

sentence-transformers · Kit

Turns sentences and paragraphs into 384-number vectors for semantic search, clustering and sentence similarity, with a multilingual model from the sentence-tra…

SenseNova-U1.5-8B-MoT

sensenova · Kit

A unified multimodal model for creating and editing images, with legible Chinese and English text, native 4K output and control through boxes and reference ima…

Jasper-K-35B-MoE

ragentile · Kit

Writes GPU kernels and improves their speed through repeated tries against a test environment. A mixture-of-experts model trained from Qwen3.6-35B-A3B with rei…

Jasper-K-32B

ragentile · Kit

Writes GPU kernels and improves their speed through repeated tries against a test environment. A 32B model trained from QwQ-32B with reinforcement learning, fo…

Qwen3.5-4B-Base

Qwen · Kit

Gives researchers a pre-trained-only vision-language base model for fine-tuning and in-context learning experiments, not for direct chat. Suits developers who…

Qwen3-14B

Qwen · Kit

Reasons through hard problems in a thinking mode and answers everyday chat in a faster non-thinking mode, as a 14.8B-parameter open model. Suits developers who…

Qwen2.5-Coder-32B-Instruct

Qwen · Kit

Writes, explains and fixes code as the largest instruction-tuned model in the Qwen2.5-Coder family, at 32B parameters. For developers who run a strong open cod…

Qwen-Image

Qwen · Kit

Turns written prompts into images and renders readable text inside them, in English and Chinese. Suits designers, artists and developers who work with the diff…

Pipecat backchannel detector

pipecat-ai · Kit

Listens to a user while a voice bot is talking and tells apart a quick "mm-hmm" from a real interruption, so the bot keeps going or stops. A tiny streaming aud…

PaddleOCR-VL

PaddlePaddle · Kit

Reads document images and returns their text, in a vision-language model under one billion parameters. For people who parse English and Chinese documents with…

ARLoop-0.6B

osunlp · Kit

Completes text as a small pretrained looped transformer with attention residuals. A base model for researchers who want to continue its training with their own…

Ornith-1.5-9B

ornith-ai · Kit

Handles coding and terminal tasks as a 9B dense language model sized for a single GPU. For developers who want a small open model for software work, with a mob…

Ornith-1.5-122B-NVFP4

ornith-ai · Kit

Gives you an NVFP4 quantized copy of Ornith-1.5-122B, a 122B mixture-of-experts text model meant for single-GPU use and strong in coding tests. For developers…

MiniCPM-V 4.6

openbmb · Kit

Reads single images, several images and video and answers in text, with 1.3B parameters sized for phones and other edge devices. For developers who want a smal…

OpenAI Privacy Filter

openai · Kit

Finds and masks personal information such as names and emails in text in a single pass, and runs on your own machine. For teams that need to clean large amount…

GPT-2 XL

openai-community · Kit

Continues English text from a starting phrase, as the 1.5B-parameter version of OpenAI's GPT-2. It suits researchers and developers who want a classic open tex…

EmbeddingGemma 2 Typed Decisions

mrm8488 · Kit

A 272M model, fine-tuned from EmbeddingGemma 2, that reads the state of a workflow and a schema of questions and returns a typed answer with a calibrated confi…

AREX-2 GGUF

mradermacher · Kit

GGUF quantized files of BAAI's AREX-2, a 26.9B model, from 2-bit to 8-bit with an optional multi-modal supplement. They suit people who run a large model local…

voyage-4-nano

MongoDB · Kit

Multilingual text embedding model of 346M parameters from the Voyage 4 series, for semantic search and retrieval, with flexible vector sizes. For developers bu…

DeepSeek-V4.1-Flash-1017-oQ4e-mtp

mlx-community · Kit

A mixed-precision MLX copy of DeepSeek-V4.1-Flash-1017, a huge multimodal mixture-of-experts model. Made for people with hundreds of GB of memory who want to r…

Florence-2-base

microsoft · Kit

A small Microsoft vision model that handles captioning, object detection and segmentation by changing the text prompt. It suits developers and researchers who…

LongCat-Video

meituan-longcat · Kit

Makes videos from a text prompt, from a still image, or by continuing an existing clip, with one 13.6B model. Aims at long clips at 720p and 30 fps, for develo…

MERT-v2-FullSong

m-a-p · Kit

A music encoder that turns whole songs of 30 to 360 seconds into numeric features at frame or recording level. It suits music AI researchers and developers wor…

SlideOn

lightonai · Kit

An English sparse retrieval model from LightOn that turns queries and documents into sparse vectors for inverted-index search. It suits search engineers and de…