AI projects from Hugging Face

GLiNER2.5 Base

fastino · Kit

Pulls entities, relations and structured records out of English text, and classifies it, from one schema, running locally on CPU, CUDA or MPS. It suits develop…

Mega-ASR

zhifeixie · Kit

Transcribes English and Chinese speech from noisy, echoey, clipped or overlapping recordings, and routes clean audio to the base model. For teams with difficul…

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…

t5-base-grammar-correction

vennify · Kit

Rewrites English text with fewer grammar mistakes, using a T5 model trained on the JFLEG dataset. Made by vennify for writers, students and developers who want…

F5-TTS

SWivid · Kit

Turns text into speech with the F5-TTS flow-matching model, shipped as F5-TTS and E2 TTS base checkpoints. For developers and researchers working under a non-c…

System One Model

stephenlb · Kit

Answers yes/no, multiple-choice and score questions about a text with a probability for each answer, using a Gemma 4 12B base with a small decision head. For d…

Spark-TTS-0.5B

SparkAudio · Kit

Speaks Chinese and English from text with a Qwen2.5-based model, including zero-shot voice cloning and virtual voices set by gender, pitch and speaking rate. F…

Qwen3.8-27b-Terse-Coder-LoRA

Shockem · Kit

Cuts the length of Qwen3.8-27B's reasoning on coding tasks so answers arrive sooner, as a small LoRA adapter. For people who run the base model on their own ha…

Qwen2.5-Coder-7B

Qwen · Kit

Completes and generates code as a 7.6B base language model that developers can run, fine-tune or use for fill in the middle tasks. Built for people making codi…

Qwen2.5-0.5B

Qwen · Kit

The smallest base model in Qwen2.5, about 494M parameters with a 32,768-token context, meant for further training on your own data. For developers who want a t…

deberta-v3-base-prompt-injection-v2

protectai · Kit

Flags English text that tries to hijack a language model, labeling each input as benign or prompt injection. For developers who screen user input in LLM apps.

OpenEuroLLM Prelude-base 9B

openeurollm · Kit

Intermediate checkpoints of an experimental 9B base language model trained on 10T tokens, mostly English with a multilingual share. For researchers who follow…

BERTimbau Base

neuralmind · Kit

A BERT model pretrained on Brazilian Portuguese that fills in masked words and produces text embeddings. For NLP developers and researchers who work with Portu…

OneJev1.6-4B-GGUF

mradermacher · Kit

Quantized GGUF copies of OneJev1.6-4B, from about 2 GB to 8.5 GB, for running the model on your own computer. The card does not say what the base model is for.

JevK5-chat-mlx-4bit

mlx-community · Kit

A 4-bit MLX copy of the 4.2B JevK5 chat model for Apple Silicon, with a 262,144 token context and a small memory footprint. Made for Mac users who want a quick…

Mistral-7B-v0.1

mistralai · Kit

Generates and continues text as a 7B pretrained base model, for researchers and developers who want a starting point to test, tune or build on.

KLM 1.5

MinimaLabs · Kit

A 99M-parameter base language model trained from scratch on 100B tokens, with a hybrid attention design. Made for researchers and tinkerers who want a tiny ope…

MOSS-Image FP16-fixed

KBlueLeaf · Kit

The MOSS-Image Base and SFT image transformers with their weights rescaled so they run in fp16 without overflow, giving the same outputs. For diffusers, ComfyU…

Kandinsky S2V 1.0 Lite distilled

kandinskylab · Kit

Turns one reference image and a speech recording into an avatar video, animating the whole figure to match the speech. The distilled Lite version runs 16 steps…

granite-4.2-8b GGUF

ibm-granite · Kit

Holds GGUF copies of IBM's Granite 4.2 8B model in several quantization levels, ready for llama.cpp. For people who want to run the model locally and read its…

svd-linear-attention-roberta-base-adasplash

Hooshaai · Kit

Classifies English text, such as SST-2 sentiment, with a RoBERTa Base model whose attention is made sparse by AdaSplash, trading some accuracy for lower latenc…

roberta-base-fwsvd-rank32

Hooshaai · Kit

Classifies English text with a RoBERTa Base model shrunk to about 82M parameters by Fisher-weighted SVD at rank 32, trading some accuracy for lower latency and…

roberta-base-adasplash

Hooshaai · Kit

A RoBERTa Base sentiment classifier whose attention is swapped for a sparse AdaSplash version, which zeroes out 40% of attention weights to cut time and memory…

T5 Base

google-t5 · Kit

A 220 million parameter text-to-text model that handles translation between English, French, Romanian and German, and also summarization, question answering an…

BERT multilingual base model (cased)

google-bert · Kit

Fills in masked words and extracts text features in 104 languages. A case-sensitive BERT base model meant to be fine-tuned for classification, tagging and ques…

bert-base-chinese

google-bert · Kit

Predicts masked words in Chinese text, as Google's BERT base model pre-trained for Chinese. It suits developers and researchers who build Chinese language tool…

FireRedVAD

FireRedTeam · Kit

Detects speech, singing and music in audio, with streaming and file-based voice activity detection plus audio event detection. For speech developers who segmen…

GLiNER2 base

fastino · Kit

Extracts entities, classifies text, pulls out structured data and finds relations in plain text, with one small model that runs on a CPU. It suits developers w…

Wav2Vec2-Base-960h

facebook · Kit

Turns English speech audio sampled at 16 kHz into text. A base wav2vec 2.0 model fine-tuned on 960 hours of Librispeech, for developers and researchers who nee…

Kvark-Sparkle-1.0-27B

Egzakta · Kit

Reasons over images and text with fewer thinking tokens than its base Qwen3.8-27B, so answers arrive in about half the time at similar accuracy, per its card.…

CyberRealistic XL

cyberdelia · Kit

Generates photorealistic images from text prompts, tuned for portraits, fashion and editorial scenes. An SDXL 1.0 based checkpoint for artists and designers wh…

bge-base-en-v1.5

BAAI · Kit

Turns English text into number vectors for search and retrieval. A 109M-parameter embedding model from BAAI, for developers who build semantic search or retrie…

GPT-X3-150M

AxiomicLabs · Kit

A 149M-parameter base text model from Axiomic Labs that continues the text you give it. The card reports an Intelligence Index of 33.05, ahead of SmolLM2-135M…

ModernBERT-base

answerdotai · Kit

Predicts a hidden word in English text or code, and after fine-tuning serves as a long-context encoder for search, classification and retrieval. Made for devel…

G4-MeroMero-v2-31B

zerofata · Kit

A 31.3B model by zerofata built on Gemma 4 31B instruct, for people who want to try this tune or compare it with its base. The card text says little about its…

Qwen-Video-Edit by yunpeng1998

yunpeng1998 · Kit

Edits video from written instructions by reusing an image editing model on video latents, with light trainable projections. For video creators and researchers…

Chroma1-HD

lodestones · Kit

Turns a text prompt into an image with an 8.9B open base model built on FLUX.1-schnell, made as a starting point for artists and developers who want to finetun…

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…

Wan2.2-Fun-5B-Control

alibaba-pai · Kit

Steers generated video with a control condition such as Canny, Depth, Pose or MLSD, or with a trajectory. For video creators and researchers working with the 5…

Occamy-1.0

Accio-Lab · Kit

An open 35B image and text model from Accio-Lab, based on Qwen3.6-35B-A3B, in BF16, GGUF, FP8, NVFP4 and MLX formats. For teams that serve a large model.

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…

MageTrail

RicemanT · Kit

Generates illustrations from booru-style tag prompts as a 2.8B-parameter fine-tune of the MageFlow 4B image model. Suits hobbyists and researchers who use Comf…

Qwen3-1.7B-Base

Qwen · Kit

Continues text and code as a 1.7B base language model pre-trained on 119 languages. For developers who want a small model to fine-tune or test.

Kronos-Tokenizer-base

NeoQuasar · Kit

Converts candlestick price data into discrete tokens that the Kronos forecasting models read. It suits people who forecast financial markets in Python.

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…

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…

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…

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…

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…

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.