AI projects from Hugging Face

Beam-1.0-501B-A23B

reflection · Kit

An open instruction-tuned text model from Reflection with 501B parameters, 23B active at a time and a 1M-token context, aimed at coding, tool use and reasoning…

Qwen3.5-9B-Base

Qwen · Kit

Gives researchers and developers a pre-trained 9B base model with a vision encoder, meant for fine-tuning and experiments rather than direct chat. Handles text…

Qwen3-4B

Qwen · Kit

Generates text with a 4B Qwen3 model that switches between a thinking mode for hard reasoning and a plain mode for quick chat. Suits developers who want a smal…

pplx-decider-flash-v1.2

perplexity-ai · Kit

A small Perplexity decision model built on Qwen3.5-4B that reads text and images and answers choice, yes-or-no and score questions with probabilities, for fast…

PaddleOCR-VL-1.6

PaddlePaddle · Kit

Reads an image and returns its text, built for parsing documents in English and Chinese. A 959M-parameter model from PaddlePaddle that runs through the PaddleO…

Qwen3.5-0.8B-weight-space-programming by ML-Intern-lab

ML-Intern-lab · Kit

Solves math problems step by step with a small Qwen3.5-0.8B model whose weights an LLM edited directly, with no training, to stop repetition loops. For researc…

Maya 2 Native

maya-research · Kit

Speaks text aloud in 11 Indian languages and English at 24 kHz, streaming audio as it is made, with 20 built-in voices and cross-lingual voice cloning. An open…

Qwen3.8 13.5B

kusuriya-labs · Kit

An experiment that prunes Qwen3.8-27B to half its layers and retrains it, giving a 14.7B model for Japanese and English that the author says is not practical y…

Ling-3.0-tiny

inclusionAI · Kit

Generates text with a 7.9B hybrid reasoning model that activates only 1.3B parameters per token, so it fits local and low-resource setups. Suits developers who…

Hemmingway-1.5

HemmingwayAI · Kit

Writes everyday text such as emails, blog posts and product descriptions, and rewrites other AI text in a more personal voice. An open-weights model of about 2…

gemma-4-E2B-it

google · Kit

Handles text, image and audio input and writes text, with a 128K-token context and support for over 140 languages. The smallest instruction-tuned Gemma 4 model…

DeepSeek-V4-Flash

deepseek-ai · Kit

DeepSeek's preview mixture-of-experts language model with 284B parameters, 13B used per token and a one million token context. The smaller sibling of DeepSeek-…

MiMo-V2.6-Pro-RL

XiaomiMiMo · Kit

Works with text, images, video and audio in one 1.02T-parameter model that has a 1M token context. The flagship of Xiaomi's MiMo-V2.6 series, trained with larg…

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…

MiniCPM-OCR 1.0

openbmb · Kit

A 1.3B model from OpenBMB that reads documents in English and Chinese, parsing text, tables, formulas, charts and seals and pulling out key fields.

whisper-large-v3-turbo

openai · Kit

OpenAI's faster Whisper model for speech recognition and speech translation, with 809M parameters and only 4 decoding layers. For developers and anyone who tra…

gpt-oss-120b

openai · Kit

An open-weight OpenAI language model with 117B parameters, adjustable reasoning effort, visible chain of thought and tool use. Runs on one 80 GB GPU and ships…

KURE-Sparse-nano

nlpai-lab · Kit

A compact Korean and English sparse retrieval model that turns queries and documents into sparse vectors for search over an inverted index, for teams building…

gemma-4-E4B

google · Kit

Google DeepMind's E4B model from the Gemma 4 family, an open model that takes text, images and audio and writes text, built to run on laptops and phones.

Clef-Flash

Cloudflare · Kit

Turns a state and a set of typed questions into decisions, returning a probability for every option of every question in one pass, with no free text. A 9B mult…