Open-Weight AI Models to Run Locally
Open LLMs such as Qwen3 and DeepSeek, plus models for code, images, video, speech and search, with weights you can download and run yourself.
Subcategories
- Coding Models(8 tools)
- Computer Vision Models(31 tools)
- Embedding and Reranker Models(20 tools)
- Image Generation Models(29 tools)
- Music and Sound Models(12 tools)
- Open-Weight LLMs(29 tools)
- Speech-to-Text Models(12 tools)
- Text-to-Speech Models(34 tools)
- Video Generation Models(19 tools)
- Vision-Language Models(31 tools)
A local AI image generation framework creates portraits from a reference face with FLUX and ComfyUI; its model weights are for academic research only.
2.7KUpdated 1 year agoApache-2.0
#ControlNet#Hugging Face integration#Image-to-image
InfiniteYou generates images from a reference face and a text prompt while preserving the person's facial identity. It's a local AI framework for researchers studying personalized image generation, with model use restricted to academic research.
Face Swap and PortraitsImage Generation Models+0
An open-source local LLM for reasoning and math that runs offline, supports fine-tuning, and is available through Ollama and Hugging Face.
3.9KUpdated 2 weeks agoMIT
#Hugging Face integration#Ollama integration#Works offline
Phi-4 is Microsoft's language model for developers building applications that need complex reasoning and math problem solving. It can run on your own hardware without a cloud connection.
Open-Weight LLMs+0
A free, open-source local LLM training toolkit with dense and mixture-of-experts models, Apache 2.0 licensing, and Ollama compatibility.
65.2KUpdated 3 weeks agoApache-2.0
Linux · Web#Distributed execution#Hugging Face integration#llama.cpp backend
MiniMind is a toolkit for learners and developers who want to understand language models by training small ones on their own hardware. Its core training algorithms use native PyTorch code that you can inspect and change.
LLM Fine-TuningOpen-Weight LLMsTraining Frameworks+0
An open-source computer vision library for local image and video analysis, with object tracking, model training and exports to ONNX, TensorRT and CoreML.
63.4KUpdated 23 hours agoAGPL-3.0
#ONNX
Ultralytics YOLO is a Python computer vision library for developers building applications that interpret images and video. Models can run on hardware you control for tasks such as visual inspection, inventory monitoring and robotics perception.
Computer Vision ModelsEdge and Embedded AIInference Libraries and BindingsTraining Frameworks+0
A local text-to-speech library runs on CPU, clones voices from short recordings, and supports multilingual speech on Windows, macOS and Linux.
16.9KUpdated 2 days agoApache-2.0
macOS · Windows · Linux#GGUF#Hugging Face integration#llama.cpp backend
KittenTTS is a Python text-to-speech library for developers adding local speech generation to apps or producing spoken audio from text. It supports voice cloning without model training and doesn't require a GPU.
Inference Libraries and BindingsText-to-Speech and AudiobooksText-to-Speech ModelsVoice Cloning and Voice Changers+0
An open-source voice cloning tool that generates multilingual speech from short audio clips, with emotion and accent control under the MIT license.
38.2KUpdated 2 years agoMIT
#Multilingual#Voice cloning
OpenVoice generates speech in a reference speaker's voice from a short audio clip. It's for developers and creators who need the same voice across languages or want to vary its delivery without changing the speaker.
Text-to-Speech and AudiobooksText-to-Speech ModelsVoice Cloning and Voice Changers+0
Open-source animal pose estimation software for 2D and 3D tracking. Runs on Linux or WSL with an NVIDIA GPU and includes a labeling and evaluation GUI.
322Updated 2 weeks agoMIT
Windows · Linux
Lightning Pose is an open-source package for researchers who estimate animal poses from video for behavior analysis. It supports 2D and 3D pose estimation with single-camera and multiple-camera datasets, including footage where body parts become hidden from view.
Computer Vision ModelsData Labeling and AnnotationTraining Frameworks+0
A self-hosted reasoning LLM with a million-token context window and function calling, deployable through vLLM or Transformers.
3.2KUpdated 1 year agoApache-2.0
#Hugging Face integration#Multilingual#Tool calling
MiniMax-M1 is a reasoning model for developers building AI agents or working on coding and mathematical problems with long inputs. You can deploy it on your own infrastructure.
Coding ModelsOpen-Weight LLMs+0
AI content moderation models check LLM inputs and outputs for text and image risks, with multilingual support and MLCommons hazard categories.
4.5KUpdated 2 days ago
#Guardrails#Multilingual#Multimodal input
Llama Guard is a family of AI content moderation models for developers who need to check what users submit to an LLM and what the model returns. It supports text and image checks for applications that accept more than written prompts.
Guardrails, Security and SandboxingVision-Language Models+0
Text embedding models for semantic search and document retrieval, with compact and long-context variants under the Apache 2.0 license.
91Updated 2 years agoApache-2.0
#Hugging Face integration
Snowflake Arctic Embed is an open-source family of text embedding models for developers building semantic search and document retrieval. It represents queries and documents as vectors so a search system can match them by meaning.
Embedding and Reranker Models+0
A local AI music generator that creates full-length songs with diffusion, supports Windows, Linux and Docker, and has Apache 2.0 licensing.
2.4KUpdated 12 months agoApache-2.0
macOS · Windows · Linux · Docker#Hugging Face integration#Multimodal input
DiffRhythm is an AI music generation model for musicians and developers who want to create full-length songs on their own hardware. It uses diffusion to generate songs from lyric and reference-audio inputs.
Music and Sound ModelsMusic Generation+0
Local OCR software extracts multilingual text, page layouts and tables from documents on CPU, Apple Silicon or NVIDIA GPUs.
21.6KUpdated 2 days agoApache-2.0
macOS · Web#Batch processing#llama.cpp backend#Multilingual
Surya is a local OCR toolkit for developers who need text and page structure from document images. It handles multilingual documents and preserves reading order for use in document-processing applications.
Document Parsing for LLMsOCR and Document ScanningVision-Language Models+0
A local text-to-speech system supports multi-speaker generation and NVIDIA GPUs, with a Gradio interface and MIT-licensed Python code.
15.6KUpdated 2 weeks agoMIT
Docker · Web#Multilingual#Voice cloning
F5-TTS is a local text-to-speech system for developers and creators generating speech on their own hardware. Its Gradio app provides a browser interface for speech generation, with tools for training and fine-tuning models.
Fine-Tuning and TrainingText-to-Speech and AudiobooksText-to-Speech ModelsVoice Cloning and Voice Changers+0
Local V2 AI video models generate footage from text or images on your GPUs. Diffusion Forcing models also extend clips and accept start and end frames.
7.8KUpdated 10 months ago
Web#Hugging Face integration#Multimodal input
SkyReels-V2 is the downloadable video model family for developers and researchers who want to generate footage on their own GPUs. It includes Python inference code and model weights, distinct from the SkyReels web playground. Generation runs on your hardware.
AI Video GeneratorsVideo Generation Models+0
An English speech-to-text model for local NeMo inference on Linux, with punctuation, word timestamps and CC BY 4.0 weights.
18.7KUpdated 1 day agoApache-2.0
Linux · Docker#Batch processing#Hugging Face integration
Parakeet is NVIDIA's speech recognition model family. The linked English model, parakeet-tdt-0.6b-v2, is for developers building transcription services, subtitles and voice applications with a model they can run locally.
Speech-to-Text and TranscriptionSpeech-to-Text Models+0
An open-source image classification and recognition toolkit supports custom model training, image retrieval, and server or on-device deployment.
5.9KUpdated 1 month agoApache-2.0
Android#ONNX#Quantization#Semantic search
PaddleClas is a PaddlePaddle toolkit for developers and researchers building image classification and recognition applications on their own hardware. It covers fixed-category classifiers and image matching for large or frequently changing catalogs.
Computer Vision ModelsLoRA and Image Model TrainingOn-Device and In-Browser AIQuantization and Model ConversionRAG and Vector Search+0
Downloadable vision-language models answer image questions, read text and detect objects, with checkpoints for fine-tuning or common tasks.
3.6KUpdated 1 year agoApache-2.0
#Hugging Face integration#Multimodal input
PaliGemma is a family of vision-language models for developers and researchers building applications that interpret images alongside text prompts. Pretrained models need fine-tuning to produce useful results; mix models can handle common tasks without further tuning.
Fine-Tuning and TrainingVision-Language Models+0
An open-source AI image generation framework runs locally, supports ComfyUI and Diffusers, and includes fine-tuning and LoRA tools.
902Updated 6 months agoApache-2.0
Linux · Web#Batch processing#Hugging Face integration#LoRA
Lumina-Image 2.0 generates images from text on your own hardware. It's for developers, researchers and people who want a model they can use in visual workflows or adapt with their own image collections.
Image Generation ModelsImage Generator AppsLoRA and Image Model Training+0
A local AI music model and synthesis engine for Apple Silicon, with a standalone macOS app and an AUv3 plugin for digital audio workstations.
1.9KUpdated 4 months agoApache-2.0
macOS#MLX#Streaming inference
Magenta RealTime is a local AI music model and synthesis engine for musicians playing AI instruments and developers building interactive music apps. It generates a continuous audio stream on supported Apple Silicon Macs.
Inference Libraries and BindingsMusic and Sound ModelsMusic Generation+0
Downloadable coding models support local code completion and software engineering agents, with Devstral compatible with Ollama, llama.cpp and vLLM.
10.8KUpdated 5 months agoApache-2.0
Docker#Hugging Face integration#Tool calling
Codestral and Devstral are coding models for developers who want to run completion tools or software engineering agents on their own hardware. The associated mistral-inference library is archived and no longer maintained.
Coding Models+0
An open-source audio AI model for offline transcription, translation and recording Q&A, with vLLM and Transformers support under Apache 2.0.
10.8KUpdated 5 months agoApache-2.0
#Hugging Face integration#Multilingual#Multimodal input
Voxtral Small is an audio and text model for developers building self-hosted speech applications. The separate mistral-inference library is archived and no longer maintained; this model runs with vLLM or Hugging Face Transformers.
Open-Weight LLMsSpeech-to-Text and TranscriptionSpeech-to-Text ModelsTranslation+0
A family of downloadable multimodal AI models for local GPU inference through Mistral's Apache 2.0 library, which is archived.
10.8KUpdated 5 months agoApache-2.0
Docker#Hugging Face integration#Multimodal input#Tool calling
Pixtral is a family of Mistral models for developers building multimodal applications with downloaded weights. The associated mistral-inference library is archived and no longer maintained.
Vision-Language Models+0
Open-weight LLMs support self-hosted text generation, with function calling in Mistral Large and hosted inference through an API or cloud providers.
10.8KUpdated 5 months agoApache-2.0
Docker#Hugging Face integration#Multimodal input#Tool calling
Mistral Small and Large are downloadable language models for developers building chat and text applications on their own infrastructure. Their reference library, mistral-inference, is archived and no longer maintained.
Open-Weight LLMsVision-Language Models+0
LogotyperGot an idea for an AI tool? I'm Eugene, the designer and developer behind Localhosted. I'll help you build it, from the first sketch to launch.
Start your projectLogotyperGot an idea for an AI tool? I'm Eugene, the designer and developer behind Localhosted. I'll help you build it, from the first sketch to launch.
Start your project
