Open-Weight AI Models to Run Locally

HiDream-I1 is an open-source text-to-image model for people who want to generate images on their own hardware or build image generation into a Python application. It uses MIT licensing and supports local inference through CUDA, making it an option for developers and creators with NVIDIA GPU hardware.

CLIP is an open-source image and text model that lets developers and researchers classify images using labels written in natural language, without collecting training examples for each task. It runs locally through PyTorch on a CPU or CUDA GPU. The code and model weights use the MIT license.

JoyCaption is an open-weight image captioning model for people preparing datasets to train or fine-tune diffusion models. It runs on your own GPU and covers both SFW and NSFW images, including photography, anime, digital art and furry artwork. Automated captions reduce the need to write descriptions by hand or find images that already have usable text.

Parler-TTS generates speech locally, with text descriptions that control how the voice sounds. It's a Python library for developers building speech into applications and researchers who want to train or adapt a TTS model. The library uses the Apache 2.0 license and can run on CPU or CUDA GPUs, with support for Apple Silicon.

Spark-TTS is a local text-to-speech system that can copy a voice from reference audio or create a synthetic speaker with adjustable vocal traits. It's for developers and researchers building speech applications, including personalized narration, assistive technology, and language research. The Python and PyTorch code is open source under Apache 2.0.

Grounding DINO finds objects in images using category names or descriptive phrases you supply. It's a local AI model for developers and computer vision researchers who need detection beyond a fixed set of labels, including people building dataset annotation tools.

OpenCLIP is a Python and PyTorch library for developers and researchers who want to match images with text on their own hardware. It implements OpenAI's CLIP approach: images and descriptions become numerical representations that the model can compare. This supports image search and zero-shot classification, where text labels define the categories without a separate classifier trained for each task.

Tortoise TTS is a local text-to-speech system for developers and creators who want speech with varied voices and natural pacing. It uses reference audio clips to guide a custom voice, with an emphasis on expressive rhythm and intonation.

OmniGen is a local AI image generation model that handles text prompts, reference images, and image editing within one model. It's for creators who want to reuse subjects across images and developers building image tools on their own hardware. The code is open source under the MIT license.

Janus-Pro is a multimodal AI model from DeepSeek that answers questions about images and creates pictures from text prompts. It runs on your own hardware and suits developers and researchers who want both capabilities in one model. A local Gradio demo provides a browser interface, while Hugging Face hosts a separate online demo.

Lumina-Image 2.0 is a local AI image generation framework for developers, researchers and people who want to generate images from text on their own hardware. It provides downloadable checkpoints, generation code and tools for adapting the model to your own image collections. The code uses the Apache 2.0 license.

Orpheus TTS is an open-source text-to-speech system for developers building voice applications or adapting speech models to their own recordings. It runs locally and uses a Llama backbone to generate speech with control over emotion and intonation. The code uses the Apache 2.0 license.

Bark is Suno's local text-to-audio model for developers and researchers who want to generate speech alongside other sounds. It can produce laughter, crying, music and background noise within its output. Its generative approach suits audio experiments, though it can depart from the supplied script and doesn't guarantee clean, studio-quality speech.

Dia is the original text-to-speech model from Nari Labs that generates a two-speaker conversation from a written script in one pass. It's for researchers and developers who want to generate English dialogue on their own hardware, with control over speaker voices and delivery. The code and model weights are available under Apache 2.0. Dia2 is a separately linked successor.

Model2Vec turns sentence transformers into small static embedding models that run locally on CPU. It's for developers who need text embeddings for retrieval, code search or classification without the size and inference cost of the original transformer. The Python package is open source under the MIT license.

EchoMimic turns a portrait image and an audio recording into an animated talking-head video on your own hardware. Its distinguishing feature is editable facial landmark control: you can drive animation with audio, landmarks, or audio combined with selected landmarks. It's intended for academic research and suits people comparing methods for speech animation and facial motion control.

F5-TTS is a local text-to-speech system that uses a reference recording to generate new speech in that voice without training a separate model for each speaker. It's for developers, speech researchers, and creators who want to generate voices on their own hardware. Its Python code uses MIT, while pretrained models use the noncommercial CC-BY-NC license.

MusicGen is Meta AI's music generation model within AudioCraft, a PyTorch library for developers and audio researchers who want to generate music in their own computing environment. It creates music from text descriptions and can use a melody to guide the result. AudioCraft includes both inference and training code, so it's suited to people building audio tools or studying music generation.

Moonshine is an on-device AI toolkit for developers building voice agents and applications that listen and speak. It combines speech to text, intent recognition and text to speech in one library. Voice processing stays on the device, and you don't need an account or API keys.

SenseVoice is a local speech recognition model that adds language, emotion and sound-event tags to transcriptions. It's for developers building voice applications or analyzing recordings on their own hardware, particularly those working with Mandarin and Cantonese. The project is open source under the MIT license.

Detectron2 is an open-source Python library for developers and researchers building computer vision applications. It provides algorithms for locating objects in images and segmenting image regions, with support for training models and building research projects on top of the library. Facebook AI Research developed it as the successor to Detectron and maskrcnn-benchmark.

Magenta RealTime 2 is a local AI music model and synthesis engine for musicians and developers who want to play or build AI musical instruments on a laptop. It generates streaming audio in real time, with open weights and code under the Apache 2.0 license.

InsightFace is a face analysis toolkit for developers and teams building identity verification, access control, or face editing software. The code uses the MIT license. Its Python tools and self-hosted recognition server run inference on your own hardware. It also offers commercial models and API access for face swapping and deepfake detection.

OpenVoice is an open-source voice cloning tool that uses a short recording to reproduce a speaker's voice in generated speech. It's for developers and creators who need a recognizable voice across languages, with control over how that voice sounds. The Python project is MIT licensed for commercial use.

GOT-OCR2.0 is an OCR model for developers and researchers who want to extract text from images on their own hardware. It handles both plain text and formatted output through a single model, with recognition modes for selected regions and documents spanning multiple pages. The Python codebase builds on Vary.

Parakeet is NVIDIA's speech recognition model family. The linked parakeet-tdt-0.6b-v2 is its English speech-to-text model for developers and researchers building transcription services, subtitles or voice applications. It runs locally through NeMo on Linux, with NVIDIA GPUs recommended for inference. It's a model you can embed in an application, rather than a desktop transcription app.

DeepSeek-OCR is an open-source OCR model for developers building document processing tools and researchers studying how AI reads text through images. It runs on your own hardware with NVIDIA CUDA GPUs. Its distinctive focus is visual text compression: representing document images with compact sets of vision tokens for a language model to read.

Distil-Whisper is a family of local speech recognition models for developers building English transcription into their apps or services. It reduces Whisper's size and processing time while retaining much of its transcription accuracy. It supports English only.

Moshi is a voice AI model and dialogue framework that can listen while it speaks. It processes speech directly, retaining information such as emotion and non-verbal cues that a text transcription can miss. It's aimed at researchers and developers building spoken AI applications, with local inference and self-hosted server options.

MuseTalk is a local AI lip-sync model for creators and developers working on video dubbing or virtual avatars. It edits the face in an existing video to match supplied speech, including Chinese, English and Japanese audio. It runs on Windows and Linux with NVIDIA GPUs, and can process videos generated by MuseV.

Kokoro is a text-to-speech model and inference library for developers who want to generate speech on their own hardware or servers. Its compact Kokoro-82M model suits personal projects and production applications, with Apache 2.0 licensing for both the library and model weights.

Stable Diffusion 3.5 is a family of text-to-image models for people building image tools or producing visual work on their own infrastructure. It generates photography, paintings, line art and 3D-style images from prompts, with an emphasis on following the requested subject and composition.

Molmo is Ai2's family of vision-language models, with code for running and training models on your own hardware. It's for developers and researchers who need to work with images and text, adapt a model, or evaluate it against visual tasks. The Python codebase is open source under Apache 2.0 and builds on OLMo, adding image encoding and generative evaluation.

OLMo is a family of language models for researchers and developers who want to inspect, adapt or run a model on their own hardware. Weights are downloadable. Ai2 also provides the training data, code, checkpoints and reports behind the models, giving researchers material to study the full training process rather than only the finished model.

Florence-2 is Microsoft's open-source vision model for developers who want to process images on their own hardware. It handles several image tasks through text prompts, so one model can generate descriptions, read text and locate objects. It runs locally with PyTorch and Hugging Face Transformers on a CPU or CUDA GPU, and uses the MIT license.

FramePack is an open source desktop app for making videos from a still image and a written motion prompt. It runs on Windows and Linux, with generation handled by your own NVIDIA GPU. It suits people who want to make AI video locally and see the clip develop as it renders.