AI models

Turn photos of documents, multi-page scans and PDFs into text you can copy and search.

Needle is a small foundation model built specifically for devices too limited for a normal chatbot model — phones, wearables, smart-home hubs, robots and microcontrollers — packaged as a single binary as small as 8 to 29 megabytes.

Feed in past open, high, low and close prices and get a forecast of the next candles.

NanoJev is a small (0.6-billion-parameter) open reproduction of Jev: a model that reads a game or task state and a set of possible actions and returns a full probability distribution over them in one pass, with no text generation.

A cross-encoder — a model that reads two pieces of text together and judges their relationship — built by further training Qwen3.5.

Hemmingway-1 is a 27-billion-parameter language model (built on Qwen3.5) fine-tuned specifically for the everyday writing people actually do — a text to a landlord, a work email, an awkward note to a colleague — rather than the longer, hedged answers general chat models tend to give.

JEV-35B evaluates up to 256 options in one pass.

Turn photos of documents, multi-page scans and PDFs into text you can copy and search.

Convert page images of long documents into text, with all pages read together in one request.

Create or edit pictures from written requests with this open weights image model, for developers building image tools.

Create images from text or edit pictures using reference images inside ComfyUI, for people who make images and run ComfyUI themselves.

Describe a scene or attach a picture and get a single web page that draws it in interactive 3D.

Ask yes-or-no, multiple-choice or rating questions about a piece of text, JSON, an image or a video, and get a probability for every allowed answer.

This repository repackages Alibaba's Qwen-Image-2.1 image generation and editing model as single-file weights formatted specifically for ComfyUI, a popular node-based visual tool for building AI image and video pipelines by connecting boxes on a canvas rather than writing code.

CLM-v0.1-8B is an 8-billion-parameter model that scores choices, such as which action an AI agent should take next, instead of writing text.

A small model built to make decisions rather than write text.

Turn scanned PDFs and images into searchable text, Markdown, or JSON with boxes.

Give a model up to a million tokens of text and images in one go, such as a long agent session or a large pile of input, and get text back.

Use its Python encoder to format text and image chats, then run the model and get written replies.

Audio8 ASR Infinite is a speech-to-text model built for real-time, unlimited-length transcription rather than processing a finished audio file after the fact.

Chat with a large language model on your own computer or phone, even when it has little memory to spare.

Turn text into multi-speaker speech with voice cloning and continuation controls.

A 740-million-parameter embedding model from Google DeepMind that turns text, code, images, video and audio into vectors in one shared 768-dimensional space.

Sort a document into fixed answers, such as a priority level or a yes-or-no flag, and get back valid JSON in one quick step on an Apple Silicon Mac.

Run Qwen3.8-27B, a 27-billion-parameter model that reads images and text, on your own computer at a file size you choose.

Paste an AI-written email, essay or report and get a rewrite that reads more naturally, offline; for people writing in English or Chinese.

LTX-2.5 is a 22-billion-parameter open-weights model from Lightricks that generates video and sound together: describe a scene in words, or hand it a photo, and it produces a clip with a soundtrack in one pass, so picture and audio stay in sync.

Run an AI that thinks step by step and calls tools, on a laptop or your own server.

Chat with a small text model that can call tools and give structured answers, for developers building local agents or specialized apps.

For developers building voice apps: LFM3-Audio-2B turns speech into text, text into speech, and answers spoken questions in text or voice.

For developers building voice apps: LFM3-Omni-2B answers questions about photos, video and audio, and replies in text, speech or both.

Give it lyrics and a note about the style and it generates a song with vocals and backing.

Send a screenshot, chart or document and get a written explanation, or hand it a bug to fix.

Generate 4–15 second videos with built-in stereo sound from text, images, video or audio, through an online API, web app or desktop app.

Ask questions about text, images and documents, write code, and get replies in a fixed data format.

Forecast future values from numeric time-series data, including covariates and uncertainty ranges.

Run an open model that writes code and works through multi-step office tasks using tools.

Nemotron-3-Diarization is an open-weight model from NVIDIA that does speaker diarization — working out "who spoke when" in a recording — for up to eight speakers.

Send text, images or video and get written answers.

Ask questions about document images, pictures and video and get text answers; it needs NVIDIA GPU servers, so it suits developers.

Transcribe recordings up to an hour long in 40 languages, with speaker labels and timestamps, or translate speech.

Ask questions about text, images, or video and receive text responses.

Turn photos, scans and PDFs of Chinese or English documents into editable text, tables and formulas.

Ask questions about one image, several images or a video and get text answers.

A small language model — 2.5 billion parameters in a standard Llama-style architecture — built specifically for running on a device rather than in a data centre, with a 131,072-token context that is unusual at this size.

Generate images with planned text and object placement using this model for image makers, from written prompts or structured layouts.

Turn a written prompt or a JSON layout into an image, with control over where text and objects go.

Run a 27-billion-parameter reasoning model from a roughly 6 GB file on a laptop or a single GPU.

The Apple Silicon build of a heavily compressed 27-billion-parameter model, storing each weight as one of three values — minus one, zero or plus one — in an 8.6 GB download that includes a vision component.

Turn short text requests into 8-megapixel images and edit pictures on your own graphics card.

Qwen-Image-2.1 is a 7-billion-parameter image model from Alibaba's Qwen team that both generates pictures from a text description and edits existing ones in the same model, using up to 10 reference images and letting you mark local edits with circles, painted annotations or masks while preserving the identity of people and products shown.

An accelerated 7-billion-parameter image model for making pictures from text and editing an existing image.

Run a 27-billion-parameter model that reads text, images and video and writes text back, on hardware you control.

An experimental preview of the architecture Alibaba intends to build its next model generation on, released with open weights.

Let an AI model investigate code, fix bugs, add features and write tests, for developers who host their own coding agents.

Idol turns one photo, render or generated image of an object into a 3D Gaussian splat file.

Julia-1 is a 144-million-parameter decision model, tiny beside the big chat models, that takes background context, a question and a list of possible answers, then picks the right one.

ZDTaichu5.0-9B is a 9-billion-parameter vision-language model, meaning it reads images, video and text together.

Extract and update conversation facts for memory frameworks such as Mem0 or MemOS.

Run a small model on your own server that calls tools, writes code and follows instructions inside agent setups.

Get answers from a 27-billion-parameter reasoning model that spends less time thinking to itself before replying.

A compressed, ready-to-run version of Swift-Qwen3.8-27B, which is Qwen3.8-27B adjusted to reach its answers with far less internal deliberation.

Unsloth’s release repackages Qwen-Image-2.1 — the open image-generation model — into GGUF files, the compact format that runs on ordinary computers through tools like llama.cpp and Stable Diffusion.cpp instead of demanding a datacenter GPU.

Compressed builds of Qwen3.8-27B, Alibaba’s 27-billion-parameter model that reads images and video as well as text, packaged as GGUF files so they run through llama.cpp, Ollama or LM Studio on hardware that could not hold the original.

Viggle’s turbo build is a distilled, faster version of Qwen-Image-2.1, the open image model: where the original takes 40 passes to render a picture, this one takes about six, which Viggle reports makes it roughly five times faster from prompt to finished image.

Run a compact language model on your own device for coding, tool-using agents and long inputs; for developers building on-device AI apps.

MiMo-V2.6-Distill-Qwen-9B is a 9-billion-parameter model made by fine-tuning Qwen3.5-9B on data generated by Xiaomi's larger MiMo-V2.6 models, a technique called distillation where a smaller model is trained to imitate a bigger one's outputs rather than being trained on raw internet text from scratch.

Give one model text, images, video or audio, with up to a million tokens of context such as a whole code repository or a long tool log, and get text back for coding and agent work.

MiMo-V2.6-Pro-RL is Xiaomi's flagship model in the MiMo-V2.6 family, reading and generating text, images, video and audio in one model with a 1-million-token context for handling large codebases or long multi-session agent work.

TeleOCR is a vision-language model of about 1.2 billion parameters (learned settings) for reading documents.

Run a language model that plans several steps, calls tools and works through long coding or research tasks, using a context of 256,000 tokens.

Ask a model questions about text or images and read written answers, through the Z.ai API or on your own servers.