Open Vision-Language Models (VLMs)
Models that read images, screenshots and scanned documents and answer questions about them, such as Qwen2.5-VL and MiniCPM-V.
A family of AI models for self-hosted agents, with open weights and training data, supporting Ollama and llama.cpp on NVIDIA GPUs.
2.3KUpdated 1 week agoApache-2.0
Linux#GGUF#Guardrails#Hugging Face integration
Nemotron is NVIDIA's family of AI models for developers building agents that reason, write code and use tools. Teams can evaluate and adapt the models using published weights, training data and training recipes.
Datasets and Synthetic DataEmbedding and Reranker ModelsLLM Fine-TuningOpen-Weight LLMsVision-Language Models+0
A Python library runs and trains CLIP image-text models locally, with local checkpoint loading, Hugging Face weights and multi-GPU training.
14.3KUpdated 4 days ago
#Hugging Face integration#Multimodal input
OpenCLIP is a Python library for developers and researchers building image-text matching and zero-shot classification applications. It supports pretrained CLIP models and training models on your own hardware.
Embedding and Reranker ModelsInference Libraries and BindingsTraining FrameworksVision-Language Models+0
An open-source AI model family you can run locally through Ollama or LM Studio, with language, vision and speech models under Apache 2.0.
44Updated 2 months agoApache-2.0
Linux#Guardrails#Hugging Face integration#LM Studio integration
Granite is IBM's family of AI models for developers and businesses building applications on their own hardware or servers. You can customize the models for enterprise tasks, including coding assistants and document analysis.
Coding ModelsEmbedding and Reranker ModelsOpen-Weight LLMsSpeech-to-Text ModelsVision-Language Models+0
A local vision language model answers image questions, writes captions and locates objects, with open weights and optional hosted inference.
10.2KUpdated 7 months agoApache-2.0
macOS · Windows · Linux#Hugging Face integration#Multimodal input#Works offline
Moondream is a vision language model for developers building apps that interpret images, such as warehouse or manufacturing footage. Its downloadable models can run on your own hardware, including offline in an air-gapped environment.
Computer Vision ModelsEdge and Embedded AIInference Libraries and BindingsVision-Language Models+0
A local OCR model processes images and PDFs through vLLM or Hugging Face Transformers, with CUDA inference and an MIT license.
24.2KUpdated 10 months agoMIT
Linux#Batch processing#Hugging Face integration#Multimodal input
DeepSeek-OCR is an OCR model for developers processing document images and PDFs on their own hardware. It also supports research into visual text compression, representing text-bearing images with compact sets of vision tokens.
Document Parsing for LLMsOCR and Document ScanningVision-Language Models+0
A local LLM family with downloadable text and vision models, base and chat variants, and custom licensing for research and commercial use.
7.7KUpdated 1 year ago
#Hugging Face integration#Multimodal input#Quantization
Llama is Meta's family of language models for developers, researchers and businesses building AI applications on their own hardware or servers. Downloadable weights let you choose a model for your application and available hardware.
Open-Weight LLMsVision-Language Models+0
Local vision-language models answer image prompts, with PyTorch checkpoints and on-device inference on iPhone, iPad and Apple Silicon Macs.
7.4KUpdated 2 months ago
macOS · iOS#Multimodal input#Quantization
FastVLM is a family of local vision-language models for developers and researchers building applications that answer questions about images. It focuses on reducing the delay before an answer starts, especially with high-resolution images.
LLM Fine-TuningOn-Device and In-Browser AIQuantization and Model ConversionVision-Language Models+0
A world-model platform for robotics and autonomous vehicles, with downloadable NVIDIA GPU models for visual reasoning, simulation and synthetic video.
12.4KUpdated 4 days ago
#Guardrails#Hugging Face integration#Multimodal input
NVIDIA Cosmos provides world models for developers building robots, autonomous vehicles and industrial vision systems. It supports reasoning about physical scenes, generating training data and learning actions before real-world deployment.
Datasets and Synthetic DataEdge and Embedded AIVideo Generation ModelsVision-Language Models+0
A local image captioning model with open weights, SFW and NSFW coverage, and integrations for ComfyUI and vLLM.
1.3KUpdated 9 months agoApache-2.0
Windows · Docker#Hugging Face integration#Multimodal input#OpenAI-compatible API
JoyCaption generates image descriptions for people preparing datasets to train or fine-tune diffusion models. It can caption images on your own GPU, reducing the work of writing training descriptions by hand.
Data Labeling and AnnotationPhoto Search and Auto-TaggingVision-Language Models+0
A local vision-language model connects text with specific image regions, uses Vicuna checkpoints, and runs GPU inference with a Gradio browser interface.
8.6KUpdated 2 months ago
Web#Multimodal input
Ferret is a local vision-language model for researchers studying how AI understands specific parts of an image. It supports questions about selected regions and can identify image regions in its answers. Its code and data are restricted to research use.
LLM Evaluation and TestingLLM Fine-TuningVision-Language Models+0
A self-hosted vision-language model project for image chat and visual reasoning, with local inference and checkpoint-specific licensing.
25.1KUpdated 3 years agoApache-2.0
macOS · Web#LoRA#Multimodal input#Quantization
LLaVA is a vision-language model project for researchers and developers who want to ask questions about images on their own hardware.
Datasets and Synthetic DataLLM Fine-TuningSelf-Hosted Chat Web UIsVision-Language Models+0
Local vision-language models interpret images, video and text on your own hardware, with mobile deployment and support for Ollama and llama.cpp.
27.1KUpdated 6 days agoApache-2.0
macOS · iOS · Android · Web#GGUF#Hugging Face integration#llama.cpp backend
MiniCPM-V is a family of local vision-language models for developers building applications that interpret images and video. It can run on phones and other hardware you control.
On-Device and In-Browser AIVision-Language Models+0
An open source OCR toolkit runs locally and converts PDFs and images into Markdown or JSON, with multilingual recognition and an Apache 2.0 license.
92.7KUpdated 2 months agoApache-2.0
Web#Multilingual#ONNX#Structured output
PaddleOCR is an OCR and document parsing toolkit for developers turning PDFs and images into data for document search, RAG systems and AI agents. Its local models cover both structured pages and text found in photographs.
Computer Vision ModelsDocument Parsing for LLMsOCR and Document ScanningVision-Language Models+0
A vision-language model family for self-hosted visual chat and image retrieval, with downloadable weights and Hugging Face Transformers support.
10.2KUpdated 1 year agoMIT
#Hugging Face integration#Multimodal input
InternVL is a family of vision-language models for developers and researchers building AI applications that interpret images and answer questions about them. Downloadable models let teams host inference themselves.
Computer Vision ModelsVision-Language Models+0
An open-source OCR model parses images and multi-page documents on NVIDIA GPUs, with Transformers, vLLM and SGLang support.
31.2KUpdated 6 days agoMIT
Docker#Batch processing#Hugging Face integration#Multimodal input
Unlimited-OCR is an OCR model for developers building document extraction workflows on their own hardware or servers. It handles individual document images and multi-page inputs, including PDFs converted to page images.
Document Parsing for LLMsOCR and Document ScanningVision-Language Models+0
An AI document parser runs locally to convert PDFs and document images into JSON and Markdown, with layout analysis and formula extraction.
9.1KUpdated 8 months ago
#Batch processing#Hugging Face integration
Dolphin Document Parser converts PDFs and document images into structured content for developers working on document extraction. It handles digitally created and photographed pages, including documents that mix text with tables, formulas, and code.
Document Parsing for LLMsOCR and Document ScanningVision-Language Models+0
Open-source vision model for local captioning, OCR and object detection, with MIT licensing and support for CPU or CUDA GPU processing.
huggingface.coComputer Vision Models
#Hugging Face integration#Multimodal input#Structured output
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.
Computer Vision ModelsOCR and Document ScanningVision-Language Models+0
An open-weight local LLM family for phones, PCs and servers, with Ollama and LM Studio support and a JAX library for fine-tuning.
5.8KUpdated 1 month agoApache-2.0
Android#LM Studio integration#LoRA#Multilingual
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.
Edge and Embedded AIEmbedding and Reranker ModelsLLM Fine-TuningOpen-Weight LLMsVision-Language Models+0
A self-hosted multilingual OCR model that extracts document text and page layout, with vLLM deployment and CPU inference support.
9.2KUpdated 8 months agoMIT
Docker#Hugging Face integration#Multilingual#Multimodal input
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.
Document Parsing for LLMsOCR and Document ScanningVision-Language Models+0
A local vision language model processes images and text with Hugging Face Transformers, supports multiple images per chat, and uses the Apache 2.0 license.
4KUpdated 1 month agoApache-2.0
#Hugging Face integration#LoRA#Multimodal input
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.
On-Device and In-Browser AIVision-Language Models+0
A local vision-language model family with Python tools for training and evaluation, OLMo and Qwen2 backbones, and Apache 2.0 code.
946Updated 2 years agoApache-2.0
#Hugging Face integration#Multimodal input#Works offline
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.
LLM Evaluation and TestingTraining FrameworksVision-Language Models+0
A local AI object detection model finds objects from text descriptions and returns bounding boxes, with PyTorch support for CPU or CUDA hardware.
10.8KUpdated 2 years agoApache-2.0
Docker · Web#Hugging Face integration#Multimodal input
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.
Computer Vision ModelsVision-Language Models+0
An open-source image classification model that matches pictures to text labels without task-specific training and runs locally on CPU or CUDA GPUs.
34.6KUpdated 8 months agoMIT
#Batch processing#Multimodal input
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.
Computer Vision ModelsEmbedding and Reranker ModelsVision-Language Models+0
A local vision-language model analyzes images, extracts document data and locates video events, with Apache 2.0 weights and Transformers support.
huggingface.coOCR and Document Scanning
Linux#Batch processing#Hugging Face integration#Multimodal input
Qwen2.5-VL is a vision-language model for developers building visual assistants, document processing applications and screen-based agents. It answers questions about images and video and can return structured data for software to use.
OCR and Document ScanningVision-Language Models+0
A multimodal AI model family that understands text, images, video and audio, with an Omni model that generates text, images and speech.
1.1KUpdated 3 months ago
#Image-to-image#LoRA#Multimodal input
Uni MoE is a family of multimodal AI models for researchers working with language, visual material and audio together. Its Omni model can reason across combined inputs and answer questions about their content.
Image Generation ModelsMusic and Sound ModelsSpeech-to-Text ModelsText-to-Speech ModelsVision-Language Models+0
A local multimodal AI model answers image questions and generates pictures from text, with downloadable weights and a Gradio browser interface.
17.8KUpdated 2 years agoMIT
Web#Batch processing#Hugging Face integration#Multimodal input
Janus-Pro is a multimodal AI model for developers and researchers who want to interpret images and generate pictures on their own hardware. It combines both tasks in one model.
Image Generation ModelsVision-Language Models+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
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
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
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
