[go: up one dir, main page]

Browse free open source Python AI Models and projects below. Use the toggles on the left to filter open source Python AI Models by OS, license, language, programming language, and project status.

  • Monitor your whole IT Infrastructure Icon
    Monitor your whole IT Infrastructure

    Know what's up and what's new: Monitor all your systems, devices, traffic and applications.

    Caters to tech staff, system Administrators, and companies of any size, from small and medium sized businesses to enterprises that need their IT network to be reliable and easy to monitor in real-time. Equipped with an easy-to-use, intuitive interface with a cutting-edge monitoring engine. PRTG optimizes connections and workloads as well as reducing operational costs by avoiding outages while saving time and controlling service level agreements (SLAs).
    Start Your Free PRTG Trial Now
  • Cloud-based observability solution that helps businesses track and manage workload and performance on a unified dashboard. Icon
    Cloud-based observability solution that helps businesses track and manage workload and performance on a unified dashboard.

    For developers, engineers, and operational teams in organizations of all sizes

    Monitor everything you run in your cloud without compromising on cost, granularity, or scale. groundcover is a full stack cloud-native APM platform designed to make observability effortless so that you can focus on building world-class products. By leveraging our proprietary sensor, groundcover unlocks unprecedented granularity on all your applications, eliminating the need for costly code changes and development cycles to ensure monitoring continuity.
    Learn More
  • 1
    GLM-4.5

    GLM-4.5

    GLM-4.5: Open-source LLM for intelligent agents by Z.ai

    GLM-4.5 is a cutting-edge open-source large language model designed by Z.ai for intelligent agent applications. The flagship GLM-4.5 model has 355 billion total parameters with 32 billion active parameters, while the compact GLM-4.5-Air version offers 106 billion total parameters and 12 billion active parameters. Both models unify reasoning, coding, and intelligent agent capabilities, providing two modes: a thinking mode for complex reasoning and tool usage, and a non-thinking mode for immediate responses. They are released under the MIT license, allowing commercial use and secondary development. GLM-4.5 achieves strong performance on 12 industry-standard benchmarks, ranking 3rd overall, while GLM-4.5-Air balances competitive results with greater efficiency. The models support FP8 and BF16 precision, and can handle very large context windows of up to 128K tokens. Flexible inference is supported through frameworks like vLLM and SGLang with tool-call and reasoning parsers included.
    Downloads: 528 This Week
    Last Update:
    See Project
  • 2
    GLM-4.6

    GLM-4.6

    Agentic, Reasoning, and Coding (ARC) foundation models

    GLM-4.6 is the latest iteration of Zhipu AI’s foundation model, delivering significant advancements over GLM-4.5. It introduces an extended 200K token context window, enabling more sophisticated long-context reasoning and agentic workflows. The model achieves superior coding performance, excelling in benchmarks and practical coding assistants such as Claude Code, Cline, Roo Code, and Kilo Code. Its reasoning capabilities have been strengthened, including improved tool usage during inference and more effective integration within agent frameworks. GLM-4.6 also enhances writing quality, producing outputs that better align with human preferences and role-playing scenarios. Benchmark evaluations demonstrate that it not only outperforms GLM-4.5 but also rivals leading global models such as DeepSeek-V3.1-Terminus and Claude Sonnet 4.
    Downloads: 346 This Week
    Last Update:
    See Project
  • 3
    Wan2.2

    Wan2.2

    Wan2.2: Open and Advanced Large-Scale Video Generative Model

    Wan2.2 is a major upgrade to the Wan series of open and advanced large-scale video generative models, incorporating cutting-edge innovations to boost video generation quality and efficiency. It introduces a Mixture-of-Experts (MoE) architecture that splits the denoising process across specialized expert models, increasing total model capacity without raising computational costs. Wan2.2 integrates meticulously curated cinematic aesthetic data, enabling precise control over lighting, composition, color tone, and more, for high-quality, customizable video styles. The model is trained on significantly larger datasets than its predecessor, greatly enhancing motion complexity, semantic understanding, and aesthetic diversity. Wan2.2 also open-sources a 5-billion parameter high-compression VAE-based hybrid text-image-to-video (TI2V) model that supports 720P video generation at 24fps on consumer-grade GPUs like the RTX 4090. It supports multiple video generation tasks including text-to-video.
    Downloads: 127 This Week
    Last Update:
    See Project
  • 4
    DeepSeek R1

    DeepSeek R1

    Open-source, high-performance AI model with advanced reasoning

    DeepSeek-R1 is an open-source large language model developed by DeepSeek, designed to excel in complex reasoning tasks across domains such as mathematics, coding, and language. DeepSeek R1 offers unrestricted access for both commercial and academic use. The model employs a Mixture of Experts (MoE) architecture, comprising 671 billion total parameters with 37 billion active parameters per token, and supports a context length of up to 128,000 tokens. DeepSeek-R1's training regimen uniquely integrates large-scale reinforcement learning (RL) without relying on supervised fine-tuning, enabling the model to develop advanced reasoning capabilities. This approach has resulted in performance comparable to leading models like OpenAI's o1, while maintaining cost-efficiency. To further support the research community, DeepSeek has released distilled versions of the model based on architectures such as LLaMA and Qwen.
    Downloads: 49 This Week
    Last Update:
    See Project
  • Cynet All-in-One Cybersecurity Platform Icon
    Cynet All-in-One Cybersecurity Platform

    All-in-One Managed Cybersecurity for MSPs

    Cynet empowers MSPs and MSSPs with a comprehensive, fully managed cybersecurity platform that consolidates essential security functions into a single, easy-to-use solution. Cynet simplifies cybersecurity management, reduces operational overhead, and lowers costs by eliminating the need for multiple vendors and complex integrations.
    Learn More
  • 5
    DeepSeek-V3

    DeepSeek-V3

    Powerful AI language model (MoE) optimized for efficiency/performance

    DeepSeek-V3 is a robust Mixture-of-Experts (MoE) language model developed by DeepSeek, featuring a total of 671 billion parameters, with 37 billion activated per token. It employs Multi-head Latent Attention (MLA) and the DeepSeekMoE architecture to enhance computational efficiency. The model introduces an auxiliary-loss-free load balancing strategy and a multi-token prediction training objective to boost performance. Trained on 14.8 trillion diverse, high-quality tokens, DeepSeek-V3 underwent supervised fine-tuning and reinforcement learning to fully realize its capabilities. Evaluations indicate that it outperforms other open-source models and rivals leading closed-source models, achieving this with a training duration of 55 days on 2,048 Nvidia H800 GPUs, costing approximately $5.58 million.
    Downloads: 45 This Week
    Last Update:
    See Project
  • 6
    Qwen3

    Qwen3

    Qwen3 is the large language model series developed by Qwen team

    Qwen3 is a cutting-edge large language model (LLM) series developed by the Qwen team at Alibaba Cloud. The latest updated version, Qwen3-235B-A22B-Instruct-2507, features significant improvements in instruction-following, reasoning, knowledge coverage, and long-context understanding up to 256K tokens. It delivers higher quality and more helpful text generation across multiple languages and domains, including mathematics, coding, science, and tool usage. Various quantized versions, tools/pipelines provided for inference using quantized formats (e.g. GGUF, etc.). Coverage for many languages in training and usage, alignment with human preferences in open-ended tasks, etc.
    Downloads: 41 This Week
    Last Update:
    See Project
  • 7
    HunyuanWorld-Voyager

    HunyuanWorld-Voyager

    RGBD video generation model conditioned on camera input

    HunyuanWorld-Voyager is a next-generation video diffusion framework developed by Tencent-Hunyuan for generating world-consistent 3D scene videos from a single input image. By leveraging user-defined camera paths, it enables immersive scene exploration and supports controllable video synthesis with high realism. The system jointly produces aligned RGB and depth video sequences, making it directly applicable to 3D reconstruction tasks. At its core, Voyager integrates a world-consistent video diffusion model with an efficient long-range world exploration engine powered by auto-regressive inference. To support training, the team built a scalable data engine that automatically curates large video datasets with camera pose estimation and metric depth prediction. As a result, Voyager delivers state-of-the-art performance on world exploration benchmarks while maintaining photometric, style, and 3D consistency.
    Downloads: 32 This Week
    Last Update:
    See Project
  • 8
    gpt-oss

    gpt-oss

    gpt-oss-120b and gpt-oss-20b are two open-weight language models

    gpt-oss is OpenAI’s open-weight family of large language models designed for powerful reasoning, agentic workflows, and versatile developer use cases. The series includes two main models: gpt-oss-120b, a 117-billion parameter model optimized for general-purpose, high-reasoning tasks that can run on a single H100 GPU, and gpt-oss-20b, a lighter 21-billion parameter model ideal for low-latency or specialized applications on smaller hardware. Both models use a native MXFP4 quantization for efficient memory use and support OpenAI’s Harmony response format, enabling transparent full chain-of-thought reasoning and advanced tool integrations such as function calling, browsing, and Python code execution. The repository provides multiple reference implementations—including PyTorch, Triton, and Metal—for educational and experimental use, as well as example clients and tools like a terminal chat app and a Responses API server.
    Downloads: 30 This Week
    Last Update:
    See Project
  • 9
    Wan2.1

    Wan2.1

    Wan2.1: Open and Advanced Large-Scale Video Generative Model

    Wan2.1 is a foundational open-source large-scale video generative model developed by the Wan team, providing high-quality video generation from text and images. It employs advanced diffusion-based architectures to produce coherent, temporally consistent videos with realistic motion and visual fidelity. Wan2.1 focuses on efficient video synthesis while maintaining rich semantic and aesthetic detail, enabling applications in content creation, entertainment, and research. The model supports text-to-video and image-to-video generation tasks with flexible resolution options suitable for various GPU hardware configurations. Wan2.1’s architecture balances generation quality and inference cost, paving the way for later improvements seen in Wan2.2 such as Mixture-of-Experts and enhanced aesthetics. It was trained on large-scale video and image datasets, providing generalization across diverse scenes and motion patterns.
    Downloads: 25 This Week
    Last Update:
    See Project
  • FusionAuth: Authentication and User Management Software Icon
    FusionAuth: Authentication and User Management Software

    Offer your users flexible authentication options, including passwords, passwordless, single sign-on (SSO), and multi-factor authentication (MFA).

    FusionAuth adds login, registration, SSO, MFA, and a bazillion other features to your app in days - not months.
    Learn More
  • 10
    Qwen3-Coder

    Qwen3-Coder

    Qwen3-Coder is the code version of Qwen3

    Qwen3-Coder is the latest and most powerful agentic code model developed by the Qwen team at Alibaba Cloud. Its flagship version, Qwen3-Coder-480B-A35B-Instruct, features a massive 480 billion-parameter Mixture-of-Experts architecture with 35 billion active parameters, delivering top-tier performance on coding and agentic tasks. This model sets new state-of-the-art benchmarks among open models for agentic coding, browser-use, and tool-use, matching performance comparable to leading models like Claude Sonnet. Qwen3-Coder supports an exceptionally long context window of 256,000 tokens, extendable to 1 million tokens using Yarn, enabling repository-scale code understanding and generation. It is capable of handling 358 programming languages, from common to niche, making it versatile for a wide range of development environments. The model integrates a specially designed function call format and supports popular platforms such as Qwen Code and CLINE for agentic coding workflows.
    Downloads: 21 This Week
    Last Update:
    See Project
  • 11
    DINOv3

    DINOv3

    Reference PyTorch implementation and models for DINOv3

    DINOv3 is the third-generation iteration of Meta’s self-supervised visual representation learning framework, building upon the ideas from DINO and DINOv2. It continues the paradigm of learning strong image representations without labels using teacher–student distillation, but introduces a simplified and more scalable training recipe that performs well across datasets and architectures. DINOv3 removes the need for complex augmentations or momentum encoders, streamlining the pipeline while maintaining or improving feature quality. The model supports multiple backbone architectures, including Vision Transformers (ViT), and can handle larger image resolutions with improved stability during training. The learned embeddings generalize robustly across tasks like classification, retrieval, and segmentation without fine-tuning, showing state-of-the-art transfer performance among self-supervised models.
    Downloads: 18 This Week
    Last Update:
    See Project
  • 12
    Demucs

    Demucs

    Code for the paper Hybrid Spectrogram and Waveform Source Separation

    Demucs (Deep Extractor for Music Sources) is a deep-learning framework for music source separation—extracting individual instrument or vocal tracks from a mixed audio file. The system is based on a U-Net-like convolutional architecture combined with recurrent and transformer elements to capture both short-term and long-term temporal structure. It processes raw waveforms directly rather than spectrograms, allowing for higher-quality reconstruction and fewer artifacts in separated tracks. The repository includes pretrained models for common tasks such as isolating vocals, drums, bass, and accompaniment from stereo music, achieving state-of-the-art results in benchmarks like MUSDB18. Demucs supports GPU-accelerated inference and can process multi-channel audio with chunked streaming for real-time or batch operation. It also provides training scripts and utilities to fine-tune on custom datasets, along with remixing and enhancement tools.
    Downloads: 15 This Week
    Last Update:
    See Project
  • 13
    llama.cpp Python Bindings

    llama.cpp Python Bindings

    Python bindings for llama.cpp

    llama-cpp-python provides Python bindings for llama.cpp, enabling the integration of LLaMA (Large Language Model Meta AI) language models into Python applications. This facilitates the use of LLaMA's capabilities in natural language processing tasks within Python environments.
    Downloads: 14 This Week
    Last Update:
    See Project
  • 14
    DeepSeek-V3.2-Exp

    DeepSeek-V3.2-Exp

    An experimental version of DeepSeek model

    DeepSeek-V3.2-Exp is an experimental release of the DeepSeek model family, intended as a stepping stone toward the next generation architecture. The key innovation in this version is DeepSeek Sparse Attention (DSA), a sparse attention mechanism that aims to optimize training and inference efficiency in long-context settings without degrading output quality. According to the authors, they aligned the training setup of V3.2-Exp with V3.1-Terminus so that benchmark results remain largely comparable, even though the internal attention mechanism changes. In public evaluations across a variety of reasoning, code, and question-answering benchmarks (e.g. MMLU, LiveCodeBench, AIME, Codeforces, etc.), V3.2-Exp shows performance very close to or in some cases matching that of V3.1-Terminus. The repository includes tools and kernels to support the new sparse architecture—for instance, CUDA kernels, logit indexers, and open-source modules like FlashMLA and DeepGEMM are invoked for performance.
    Downloads: 12 This Week
    Last Update:
    See Project
  • 15
    HunyuanImage-3.0

    HunyuanImage-3.0

    A Powerful Native Multimodal Model for Image Generation

    HunyuanImage-3.0 is a powerful, native multimodal text-to-image generation model released by Tencent’s Hunyuan team. It unifies multimodal understanding and generation in a single autoregressive framework, combining text and image modalities seamlessly rather than relying on separate image-only diffusion components. It uses a Mixture-of-Experts (MoE) architecture with many expert subnetworks to scale efficiently, deploying only a subset of experts per token, which allows large parameter counts without linear inference cost explosion. The model is intended to be competitive with closed-source image generation systems, aiming for high fidelity, prompt adherence, fine detail, and even “world knowledge” reasoning (i.e. leveraging context, semantics, or common sense in generation). The GitHub repo includes code, scripts, model loading instructions, inference utilities, prompt handling, and integration with standard ML tooling (e.g. Hugging Face / Transformers).
    Downloads: 12 This Week
    Last Update:
    See Project
  • 16
    Qwen-Image

    Qwen-Image

    Qwen-Image is a powerful image generation foundation model

    Qwen-Image is a powerful 20-billion parameter foundation model designed for advanced image generation and precise editing, with a particular strength in complex text rendering across diverse languages, especially Chinese. Built on the MMDiT architecture, it achieves remarkable fidelity in integrating text seamlessly into images while preserving typographic details and layout coherence. The model excels not only in text rendering but also in a wide range of artistic styles, including photorealistic, impressionist, anime, and minimalist aesthetics. Qwen-Image supports sophisticated editing tasks such as style transfer, object insertion and removal, detail enhancement, and even human pose manipulation, making it suitable for both professional and casual users. It also includes advanced image understanding capabilities like object detection, semantic segmentation, depth and edge estimation, and novel view synthesis.
    Downloads: 12 This Week
    Last Update:
    See Project
  • 17
    Hunyuan3D 2.0

    Hunyuan3D 2.0

    High-Resolution 3D Assets Generation with Large Scale Diffusion Models

    The Hunyuan3D-2 model, developed by Tencent, is designed for generating high-resolution 3D assets using large-scale diffusion models. This model offers advanced capabilities for creating detailed 3D models, including texture enhancements, multi-view shape generation, and rapid inference for real-time applications. It is particularly useful for industries requiring high-quality 3D content, such as gaming, film, and virtual reality. Hunyuan3D-2 supports various enhancements and is available for deployment through tools like Blender and Hugging Face. Includes a user-friendly production/studio tool (Hunyuan3D-Studio) to manipulate/animate meshes. Condition-aligned shape generation via the DiT model, so generated mesh is influenced by input images or prompts.
    Downloads: 11 This Week
    Last Update:
    See Project
  • 18
    Hunyuan3D-2.1

    Hunyuan3D-2.1

    From Images to High-Fidelity 3D Assets

    Hunyuan3D-2.1 is Tencent Hunyuan’s advanced 3D asset generation system that produces high-fidelity 3D models with Physically Based Rendering (PBR) textures. It is fully open-source with released model weights, training, and inference code. It improves on prior versions by using a PBR texture pipeline (enabling realistic material effects like reflections and subsurface scattering) and allowing community fine-tuning and extension. It supports both shape generation (mesh geometry) and texture generation modules. Physically Based Rendering texture synthesis to model realistic material effects, including reflections, subsurface scattering, etc. Cross-platform support (MacOS, Windows, Linux) via Python / PyTorch, including diffusers-style APIs.
    Downloads: 10 This Week
    Last Update:
    See Project
  • 19
    HunyuanWorld 1.0

    HunyuanWorld 1.0

    Generating Immersive, Explorable, and Interactive 3D Worlds

    HunyuanWorld-1.0 is an open-source, simulation-capable 3D world generation model developed by Tencent Hunyuan that creates immersive, explorable, and interactive 3D environments from text or image inputs. It combines the strengths of video-based diversity and 3D-based geometric consistency through a novel framework using panoramic world proxies and semantically layered 3D mesh representations. This approach enables 360° immersive experiences, seamless mesh export for graphics pipelines, and disentangled object representations for enhanced interactivity. The architecture integrates panoramic proxy generation, semantic layering, and hierarchical 3D reconstruction to produce high-quality scene-scale 3D worlds from both text and images. HunyuanWorld-1.0 surpasses existing open-source methods in visual quality and geometric consistency, demonstrated by superior scores in BRISQUE, NIQE, Q-Align, and CLIP metrics.
    Downloads: 9 This Week
    Last Update:
    See Project
  • 20
    GPT Neo

    GPT Neo

    An implementation of model parallel GPT-2 and GPT-3-style models

    An implementation of model & data parallel GPT3-like models using the mesh-tensorflow library. If you're just here to play with our pre-trained models, we strongly recommend you try out the HuggingFace Transformer integration. Training and inference is officially supported on TPU and should work on GPU as well. This repository will be (mostly) archived as we move focus to our GPU-specific repo, GPT-NeoX. NB, while neo can technically run a training step at 200B+ parameters, it is very inefficient at those scales. This, as well as the fact that many GPUs became available to us, among other things, prompted us to move development over to GPT-NeoX. All evaluations were done using our evaluation harness. Some results for GPT-2 and GPT-3 are inconsistent with the values reported in the respective papers. We are currently looking into why, and would greatly appreciate feedback and further testing of our eval harness.
    Downloads: 8 This Week
    Last Update:
    See Project
  • 21
    HunyuanCustom

    HunyuanCustom

    Multimodal-Driven Architecture for Customized Video Generation

    HunyuanCustom is a multimodal video customization framework by Tencent Hunyuan, aimed at generating customized videos featuring particular subjects (people, characters) under flexible conditions, while maintaining subject/identity consistency. It supports conditioning via image, audio, video, and text, and can perform subject replacement in videos, generate avatars speaking given audio, or combine multiple subject images. The architecture builds on HunyuanVideo, with added modules for identity reinforcement and modality-specific condition injection. Text-image fusion module based on LLaVA for improved multimodal understanding. Applicable to single- and multi-subject scenarios, video editing/replacement, singing avatars etc.
    Downloads: 8 This Week
    Last Update:
    See Project
  • 22
    Tencent-Hunyuan-Large

    Tencent-Hunyuan-Large

    Open-source large language model family from Tencent Hunyuan

    Tencent-Hunyuan-Large is the flagship open-source large language model family from Tencent Hunyuan, offering both pre-trained and instruct (fine-tuned) variants. It is designed with long-context capabilities, quantization support, and high performance on benchmarks across general reasoning, mathematics, language understanding, and Chinese / multilingual tasks. It aims to provide competitive capability with efficient deployment and inference. FP8 quantization support to reduce memory usage (~50%) while maintaining precision. High benchmarking performance on tasks like MMLU, MATH, CMMLU, C-Eval, etc.
    Downloads: 8 This Week
    Last Update:
    See Project
  • 23
    Stable Diffusion

    Stable Diffusion

    High-Resolution Image Synthesis with Latent Diffusion Models

    Stable Diffusion Version 2. The Stable Diffusion project, developed by Stability AI, is a cutting-edge image synthesis model that utilizes latent diffusion techniques for high-resolution image generation. It offers an advanced method of generating images based on text input, making it highly flexible for various creative applications. The repository contains pretrained models, various checkpoints, and tools to facilitate image generation tasks, such as fine-tuning and modifying the models. Stability AI's approach to image synthesis has contributed to creating detailed, scalable images while maintaining efficiency.
    Downloads: 68 This Week
    Last Update:
    See Project
  • 24
    HunyuanVideo-Avatar

    HunyuanVideo-Avatar

    Tencent Hunyuan Multimodal diffusion transformer (MM-DiT) model

    HunyuanVideo-Avatar is a multimodal diffusion transformer (MM-DiT) model by Tencent Hunyuan for animating static avatar images into dynamic, emotion-controllable, and multi-character dialogue videos, conditioned on audio. It addresses challenges of motion realism, identity consistency, and emotional alignment. Innovations include a character image injection module, an Audio Emotion Module for transferring emotion cues, and a Face-Aware Audio Adapter to isolate audio effects on faces, enabling multiple characters to be animated in a scene. Character image injection module for better consistency between training and inference conditioning. Emotion control by extracting emotion reference images and transferring emotional style into video sequences.
    Downloads: 7 This Week
    Last Update:
    See Project
  • 25
    AlphaFold 3

    AlphaFold 3

    AlphaFold 3 inference pipeline

    AlphaFold 3, developed by Google DeepMind, is an advanced deep learning system for predicting biomolecular structures and interactions with exceptional accuracy. This repository provides the complete inference pipeline for running AlphaFold 3, though access to the model parameters is restricted and must be obtained directly from Google under specific terms of use. The system is designed for scientific research applications in structural biology, biochemistry, and bioinformatics, enabling accurate modeling of proteins, ligands, and covalent modifications. Users can perform local predictions via Docker containers, integrating AlphaFold 3’s inference process with provided JSON input configurations. The software includes flexible options for running both data preprocessing and GPU-accelerated inference, allowing users to adapt to available computational resources.
    Downloads: 6 This Week
    Last Update:
    See Project
  • Previous
  • You're on page 1
  • 2
  • 3
  • 4
  • 5
  • Next