AI projects from Hugging Face

Clef

Cloudflare · Kit

Cloudflare's 27B multimodal model that scores the allowed answers to typed questions about a text, JSON, image or video input, instead of writing free text.

Qwen3.5-0.8B

Qwen · Kit

Reads images and text and replies in text, in a small 873M model from Qwen. For developers and researchers who want a light multimodal base to prototype with o…

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,…

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…

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…

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…

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…

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…

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…

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…

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…

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…

VideoLLaMA2

lixin4ever · Kit

A chat app for understanding media such as video, built on the VideoLLaMA2 models. Runs in the browser as a Gradio app on ZeroGPU, for people who want to ask q…

Chat With Janus-Pro-7B

deepseek-ai · Kit

Chats with DeepSeek's Janus-Pro-7B model, which can understand images and also generate them, with a 2x upscaling step on the pictures it makes. It suits peopl…

CCTV Visual RAG

alinawazmahar · Kit

Finds moments in surveillance video by typing a plain-language description, then returns the best-matching frames with their timestamps. For people who would r…

Open VLM Leaderboard

opencompass · Kit

Shows leaderboards of vision-language model scores gathered with the VLMEvalKit toolkit, with an overall ranking and separate tables for each benchmark. It sui…