Open-Weight AI Models to Run Locally

HunyuanImage is Tencent's text-to-image model for people who want to generate images on their own hardware. It handles detailed scene descriptions, including requests for lettering within an image.

Fish Speech is a self-hosted text-to-speech system for creators producing narration and developers building voice applications. Its S2 Pro model supports directed speech delivery and dialogue with multiple speakers.

Spark-TTS is a local text-to-speech system for developers and researchers building speech applications. It can reproduce a voice from reference audio or create a synthetic speaker with chosen vocal traits.

Step1X Edit edits existing images from written requests. It's for developers and researchers who want to run image editing on their own hardware, with control over the model and specialized training.

Florence-2 is Microsoft's vision model for developers building applications that describe images, extract text or locate objects on their own hardware. One model handles several image tasks selected through text prompts.

Stable Video Diffusion turns a still image into a short video clip for artwork, design and video generation research. Developers and researchers can run it on their own hardware, but text prompts can't direct the output.

FinGPT is a financial LLM framework for researchers and developers building tools that interpret market news and company information. It includes trained models, financial datasets, and tools for adapting models to specific finance tasks.

VACE is an AI video model for creators and developers who want to generate footage or edit existing clips locally. It combines reference-based generation and video editing, including changes limited to masked areas.

Stable Diffusion 1.5 is an AI image generation model for artists and developers who want to create artwork or explore design ideas on their own hardware. It can start with a text prompt or modify an existing picture.

Gemma is Google DeepMind's family of open-weight AI models for developers building applications on their own hardware. It includes compact models for mobile and IoT devices and larger models for reasoning on personal computers and servers.

Moonshine is an on-device AI toolkit for developers building voice agents and spoken interfaces. Voice processing runs on the device without an account or API keys.

BGE Embeddings is a family of models for developers who need to find relevant passages for search or retrieval-augmented generation (RAG). It includes embedding models for finding candidate text and rerankers for assessing how closely those results match a query.

dots.ocr is a self-hosted OCR model for developers and teams that need text and page structure from multilingual documents. It combines text recognition and layout parsing in a single vision-language model you can run on your own hardware.

Moshi is a voice AI model and dialogue framework for researchers and developers building spoken applications. It processes speech directly and can listen while it speaks, including information such as emotion and non-verbal cues.

PaddleDetection is a computer vision toolkit for developers building image and video analysis systems. It covers training, adapting and deploying models for uses such as inspection and traffic analysis.

SmolVLM is a compact vision language model for developers building applications that interpret images and answer questions about them. It can run on-device, including on laptops and smaller local setups.

DeepCell is an open-source Python library for researchers analyzing individual cells in biological images. It runs locally and uses TensorFlow to identify whole cells or nuclei and track cells through time-lapse movies. Its Apache 2.0 license allows users to adapt the library for their own research.

Molmo is Ai2's family of vision-language models for working with images and text on your own hardware. It's aimed at developers and researchers who want to train models or evaluate them on visual tasks.

Sesame CSM is a speech generation model for developers and researchers building voice applications on their own hardware. It generates spoken output from text and audio inputs, including earlier parts of a conversation.

Silero Models is a collection of pretrained text-to-speech models for developers adding voice output to applications or services. It suits projects that need speech generation on their own hardware, including support for Turkic and Caucasian languages.

CodeGen is a family of language models for generating programs, aimed at researchers and developers working on code generation. Salesforce AI Research studies how these models build programs through multiple rounds of prompting.

Kolors generates photorealistic images from text for creators and developers who want to run image generation on their own hardware. Developed by Kuaishou, it supports Chinese and English prompts, including descriptions of Chinese cultural content.

DeepSeek-Coder is a family of coding models for developers who want to run a model on their own hardware or build it into a coding assistant. It includes base models for completion and instruction-tuned models for coding requests written in plain language.

Step-Audio 2 is an audio AI model family for developers building voice assistants and applications that interpret recordings. It can reason about what people say and how they say it, as well as sounds beyond speech.

Model2Vec is a Python package for developers who need text embeddings for search or classification on their own hardware. It turns sentence transformers into smaller static embedding models, trading a small drop in performance for lower model size and faster CPU inference.

SeedVR is an AI video restoration project for developers and researchers processing real-world footage or AI-generated video on their own GPUs. Its SeedVR2 model restores footage in a single diffusion step, with substantial hardware demands in the supplied implementation.

Grounding DINO locates objects in images from category names or descriptive text. It's for developers and computer vision researchers building detection or annotation workflows that need labels beyond a fixed category list.

FLUX.1 is a family of image models for developers and creators who want to generate and edit images on their own hardware or servers.

CLIP is an image and text model for developers and researchers who want to classify pictures without building a labeled dataset for each task. You define the categories in natural language, and the model scores how closely each description matches an image.

XTTS v2 generates speech from text on your own hardware, using a voice recording as a reference. It's for developers adding speech to applications and researchers adapting a speech model to their own data.

gpt-oss is a pair of OpenAI reasoning models for developers who want to run a local LLM or serve models on their own hardware. The smaller model targets local and specialized applications; the larger one targets general-purpose tasks that need more reasoning.

StyleTTS 2 is a text-to-speech model for developers and speech researchers who want to generate expressive speech on their own hardware. It can choose a speaking style from the text without a reference recording.

HAT Super Resolution is a local AI image upscaling project for developers, researchers, and people working with low-resolution images. It provides pretrained Hybrid Attention Transformer models and code for training your own.

MedSAM is an open-source model for medical image segmentation that runs locally, aimed at researchers and developers working with medical scans. It builds on Meta's Segment Anything model and uses bounding boxes to identify the region you want to segment. The project uses the Apache 2.0 license and supports macOS.