Open Source Linux AI Models - Page 7
Sort By:
AI Models for Linux
View 129 business solutions-
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
$300 in Free Credit Towards Top Cloud ServicesStart your project in minutes. After credits run out, 20+ products include free monthly usage. Only pay when you're ready to scale.
-
1
Claude Code Security Reviewer
An AI-powered security review GitHub Action using Claude
The claude-code-security-review repository implements a GitHub Action that uses Claude (via the Anthropic API) to perform semantic security audits of code changes in pull requests. Rather than relying purely on pattern matching or static analysis, this action feeds diffs and surrounding context to Claude to reason about potential vulnerabilities (e.g. injection, misconfigurations, secrets exposure, etc). When a PR is opened, the action analyzes only the changed files (diff-aware scanning), generates findings (with explanations, severity, and remediation suggestions), filters false positives using custom prompt logic, and posts comments directly on the PR. It supports configuration inputs (which files/directories to skip, model timeout, whether to comment on the PR, etc). The tool is language-agnostic (it doesn’t need language-specific parsers), uses contextual understanding rather than simplistic rules, and aims to reduce noise with smarter filtering. -
2
ControlNet
Let us control diffusion models
ControlNet is a neural network architecture designed to add conditional control to text-to-image diffusion models. Rather than training from scratch, ControlNet “locks” the weights of a pre-trained diffusion model and introduces a parallel trainable branch that learns additional conditions—like edges, depth maps, segmentation, human pose, scribbles, or other guidance signals. This allows the system to control where and how the model should focus during generation, enabling users to steer layout, structure, and content more precisely than prompt text alone. The project includes many trained model variants that accept different types of conditioning (e.g., canny edge input, normal maps, skeletal pose) and produce improved fidelity in stable diffusion outputs. It is widely adopted in the community as a go-to tool for semi-automatic image generation workflows, especially when users want structure plus creative freedom. -
3
DINOv2
PyTorch code and models for the DINOv2 self-supervised learning
DINOv2 is a self-supervised vision learning framework that produces strong, general-purpose image representations without using human labels. It builds on the DINO idea of student–teacher distillation and adapts it to modern Vision Transformer backbones with a carefully tuned recipe for data augmentation, optimization, and multi-crop training. The core promise is that a single pretrained backbone can transfer well to many downstream tasks—from linear probing on classification to retrieval, detection, and segmentation—often requiring little or no fine-tuning. The repository includes code for training, evaluating, and feature extraction, with utilities to run k-NN or linear evaluation baselines to assess representation quality. Pretrained checkpoints cover multiple model sizes so practitioners can trade accuracy for speed and memory depending on their deployment constraints. -
4
DeepGEMM
Clean and efficient FP8 GEMM kernels with fine-grained scaling
DeepGEMM is a specialized CUDA library for efficient, high-performance general matrix multiplication (GEMM) operations, with particular focus on low-precision formats such as FP8 (and experimental support for BF16). The library is designed to work cleanly and simply, avoiding overly templated or heavily abstracted code, while still delivering performance that rivals expert-tuned libraries. It supports both standard and “grouped” GEMMs, which is useful for architectures like Mixture of Experts (MoE) that require segmented matrix multiplications. One distinguishing aspect is that DeepGEMM compiles its kernels at runtime (via a lightweight Just-In-Time (JIT) module), so users don’t need to precompile CUDA kernels before installation. Despite its lean design, it includes scaling strategies (fine-grained scaling) and optimizations inspired by cutting edge systems (drawing from ideas in CUTLASS, CuTe) but in a more streamlined form. -
Go From AI Idea to AI App FastAccess Gemini 3 and 200+ models. Build chatbots, agents, or custom models with built-in monitoring and scaling.
-
5
DreamCraft3D
Official implementation of DreamCraft3D
DreamCraft3D is DeepSeek’s generative 3D modeling framework / model family that likely extends their earlier 3D efforts (e.g. Shap-E or Point-E style models) with more capability, control, or expression. The name suggests a “dream crafting” metaphor—users probably supply textual or image prompts and generate 3D assets (point clouds, meshes, scenes). The repository includes model code, inference scripts, sample prompts, and possibly dataset preparation pipelines. It may integrate rendering or post-processing modules (e.g. mesh smoothing, texturing) to make the outputs more output-ready. Because 3D generation is hardware‐intensive, the repository likely also includes optimizations like quantization, pruning, or inference accelerations (e.g. using FlashMLA or DeepEP) to make the generation pipeline faster or more efficient. DreamCraft3D may also support style or attribute control (e.g. “make this object metallic,” “add textures”) via prompt conditioning or guides. -
6
GLM-4.1V
GLM-4.6V/4.5V/4.1V-Thinking, towards versatile multimodal reasoning
GLM-4.1V — often referred to as a smaller / lighter version of the GLM-V family — offers a more resource-efficient option for users who want multimodal capabilities without requiring large compute resources. Though smaller in scale, GLM-4.1V maintains competitive performance, particularly impressive on many benchmarks for models of its size: in fact, on a number of multimodal reasoning and vision-language tasks it outperforms some much larger models from other families. It represents a trade-off: somewhat reduced capacity compared to 4.5V or 4.6V, but with benefits in terms of speed, deployability, and lower hardware requirements — making it especially useful for developers experimenting locally, building lightweight agents, or deploying on limited infrastructure. Given its open-source availability under the same project repository, it provides an accessible entry point for testing multimodal reasoning and building proof-of-concept applications. -
7
GLM-TTS
Controllable & emotion-expressive zero-shot TTS
GLM-TTS is an advanced text-to-speech synthesis system built on large language model technologies that focuses on producing high-quality, expressive, and controllable spoken output, including features like emotion modulation and zero-shot voice cloning. It uses a two-stage architecture where a generative LLM first converts text into intermediate speech token sequences and then a Flow-based neural model converts those tokens into natural audio waveforms, enabling rich prosody and voice character even for unseen speakers. The system introduces a multi-reward reinforcement learning framework that jointly optimizes for voice similarity, emotional expressiveness, pronunciation, and intelligibility, yielding output that can rival commercial options in naturalness and expressiveness. GLM-TTS also supports phoneme-level control and hybrid text + phoneme input, giving developers precise control over pronunciation critical for multilingual or polyphone-rich languages. -
8
Granite TSFM
Foundation Models for Time Series
granite-tsfm collects public notebooks, utilities, and serving components for IBM’s Time Series Foundation Models (TSFM), giving practitioners a practical path from data prep to inference for forecasting and anomaly-detection use cases. The repository focuses on end-to-end workflows: loading data, building datasets, fine-tuning forecasters, running evaluations, and serving models. It documents the currently supported Python versions and points users to where the core TSFM models are hosted and how to wire up service components. Issues and examples in the tracker illustrate common tasks such as slicing inference windows or using pipeline helpers that return pandas DataFrames, grounding the library in day-to-day time-series operations. The ecosystem around TSFM also includes a community cookbook of “recipes” that showcase capabilities and patterns. Overall, the repo is designed as a hands-on companion for teams adopting time-series foundation models in production-leaning settings. -
9
HunyuanOCR
OCR expert VLM powered by Hunyuan's native multimodal architecture
HunyuanOCR is an open-source, end-to-end OCR (optical character recognition) Vision-Language Model (VLM) developed by Tencent‑Hunyuan. It’s designed to unify the entire OCR pipeline, detection, recognition, layout parsing, information extraction, translation, and even subtitle or structured output generation, into a single model inference instead of a cascade of separate tools. Despite being fairly lightweight (about 1 billion parameters), it delivers state-of-the-art performance across a wide variety of OCR tasks, outperforming many traditional OCR systems and even other multimodal models on benchmark suites. HunyuanOCR handles complex documents: multi-column layouts, tables, mathematical formulas, mixed languages, handwritten or stylized fonts, receipts, tickets, and even video-frame subtitles. The project provides code, pretrained weights, and inference instructions, making it feasible to deploy locally or on a server, and to integrate with applications. -
Go from Code to Production URL in SecondsSkip the Kubernetes configs. Cloud Run handles HTTPS, scaling, and infrastructure automatically. Two million requests free per month.
-
10
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. -
11
HunyuanVideo-I2V
A Customizable Image-to-Video Model based on HunyuanVideo
HunyuanVideo-I2V is a customizable image-to-video generation framework from Tencent Hunyuan, built on their HunyuanVideo foundation. It extends video generation so that given a static reference image plus an optional prompt, it generates a video sequence that preserves the reference image’s identity (especially in the first frame) and allows stylized effects via LoRA adapters. The repository includes pretrained weights, inference and sampling scripts, training code for LoRA effects, and support for parallel inference via xDiT. Resolution, video length, stability mode, flow shift, seed, CPU offload etc. Parallel inference support using xDiT for multi-GPU speedups. LoRA training / fine-tuning support to add special effects or customize generation. -
12
Janus
Unified Multimodal Understanding and Generation Models
Janus is a sophisticated open-source project from DeepSeek AI that aims to unify both visual understanding and image generation in a single model architecture. Rather than having separate systems for “look and describe” and “prompt and generate”, Janus uses an autoregressive transformer framework with a decoupled visual encoder—allowing it to ingest images for comprehension and to produce images from text prompts with shared internal representations. The design tackles long-standing conflicts in multimodal models: namely that the visual encoder has to serve both analysis (understanding) and synthesis (generation) roles. By splitting those pathways but keeping one unified core transformer, Janus maintains flexibility and achieves strong performance across tasks previously requiring distinct architectures. The repository includes pretrained checkpoints (for example 1.3B and 7B parameter versions), a Gradio demo, and guidance for local deployment. -
13
Kimi-Audio
Audio foundation model excelling in audio understanding
Kimi-Audio is an ambitious open-source audio foundation model designed to unify a wide array of audio processing tasks — from speech recognition and audio understanding to generative conversation and sound event classification — within a single cohesive architecture. Instead of fragmenting work across specialized models, Kimi-Audio handles automatic speech recognition (ASR), audio question answering, automatic audio captioning, speech emotion recognition, and audio-to-text chat in one system, enabling developers to build rich, multimodal audio applications without stitching together disparate components. It uses a novel model setup that combines continuous acoustic features with discrete semantic tokens to richly capture sound and meaning across speech, music, and environmental audio. -
14
LingBot-VLA
A Pragmatic VLA Foundation Model
LingBot-VLA is an open-source Vision-Language-Action (VLA) foundational AI model designed to serve as a general “brain” for real-world robotic manipulation by grounding multimodal perception and language into actionable motions. It has been pretrained on tens of thousands of hours of real robotic interaction data across multiple robot platforms, which enables it to generalize well to diverse morphologies and tasks without needing extensive retraining on each new bot. The model aims to bridge vision, language understanding, and motor control within one unified architecture, making it capable of understanding high-level instructions and generating coherent low-level actions in physical environments. Because LingBot-VLA includes not just the model weights but also a full production-ready codebase with tools for data handling, training, and evaluation, developers can adapt it to custom robots or simulation environments efficiently. -
15
MaskFormer
Per-Pixel Classification is Not All You Need for Semantic Segmentation
MaskFormer is a unified framework for image segmentation developed by Facebook Research, designed to bridge the gap between semantic, instance, and panoptic segmentation within a single architecture. Unlike traditional segmentation pipelines that treat these tasks separately, MaskFormer reformulates segmentation as a mask classification problem, enabling a consistent and efficient approach across multiple segmentation domains. Built on top of Detectron2, it supports a wide range of datasets including ADE20K, Cityscapes, COCO-Stuff, and Mapillary Vistas, and provides pretrained baselines for each. The model achieves strong performance and scalability while simplifying training and evaluation workflows. Its successor, Mask2Former, extends the same meta-architecture to achieve state-of-the-art results across all major segmentation benchmarks. MaskFormer’s modular design, dataset integration, and compatibility with existing Detectron2 models make it an essential research tool. -
16
MedGemma
Collection of Gemma 3 variants that are trained for performance
MedGemma is a collection of specialized open-source AI models created by Google as part of its Health AI Developer Foundations initiative, built on the Gemma 3 family of transformer models and trained for medical text and image comprehension tasks that help accelerate the development of healthcare-focused AI applications. It includes multiple variants such as a 4 billion-parameter multimodal model that can process both medical images and text and a 27 billion-parameter text-only (and multimodal) model that offers deeper clinical reasoning and understanding at higher capacity, making it suitable for complex tasks like medical question answering, summarization of clinical notes, or generating reports from radiology images. The multimodal versions pair a SigLIP-based image encoder pre-trained on diverse de-identified medical imaging data. -
17
Menagerie
A collection of high-quality models for the MuJoCo physics engine
MuJoCo Menagerie, developed by Google DeepMind, is a curated collection of high-quality simulation models designed for use with the MuJoCo physics engine. It serves as a comprehensive library of accurate and ready-to-use robotic, biomechanical, and mechanical models, ensuring users can perform reliable simulations without having to build or tune models from scratch. The repository aims to improve reproducibility and quality across robotics research by providing verified models that adhere to consistent design and physical standards. Each model directory contains its 3D assets, MJCF XML definitions, licensing information, and example scenes for visualization and testing. The collection spans a wide range of categories including robotic arms, humanoids, quadrupeds, mobile manipulators, drones, and biomechanical systems. Users can access models directly via the robot_descriptions Python package or by cloning the repository for use in interactive MuJoCo simulations. -
18
Mesh R-CNN
code for Mesh R-CNN, ICCV 2019
Mesh R-CNN is a 3D reconstruction and object understanding framework developed by Facebook Research that extends Mask R-CNN into the 3D domain. Built on top of Detectron2 and PyTorch3D, Mesh R-CNN enables end-to-end 3D mesh prediction directly from single RGB images. The model learns to detect, segment, and reconstruct detailed 3D mesh representations of objects in natural images, bridging the gap between 2D perception and 3D understanding. Unlike voxel-based or point-based approaches, Mesh R-CNN uses a differentiable mesh representation, allowing it to efficiently refine surface geometry while maintaining high spatial detail. The system combines 2D detection from Mask R-CNN with 3D reasoning modules that output full mesh reconstructions aligned with the input image. It has been evaluated on datasets such as Pix3D, where it demonstrates state-of-the-art performance in reconstructing real-world object geometry. -
19
MiniCPM-o
A GPT-4o Level MLLM for Vision, Speech and Multimodal Live Streaming
MiniCPM-o 2.6 is a cutting-edge multimodal large language model (MLLM) designed for high-performance tasks across vision, speech, and video. Capable of running on end-side devices such as smartphones and tablets, it provides powerful features like real-time speech conversation, video understanding, and multimodal live streaming. With 8 billion parameters, MiniCPM-o 2.6 surpasses its predecessors in versatility and efficiency, making it one of the most robust models available. It supports both text and audio inputs to generate outputs in various forms, including voice cloning, emotion control, and interactive role-playing. -
20
Mistral Finetune
Memory-efficient and performant finetuning of Mistral's models
mistral-finetune is an official lightweight codebase designed for memory-efficient and performant finetuning of Mistral’s open models (e.g. 7B, instruct variants). It builds on techniques like LoRA (Low-Rank Adaptation) to allow customizing models without full parameter updates, which reduces GPU memory footprint and training cost. The repo includes utilities for data preprocessing (e.g. reformat_data.py), validation scripts, and example YAML configs for training variants like 7B base or instruct models. It supports function-calling style datasets (via "messages" keys) as well as plain text formats, with guidelines on formatting, tokenization, and vocabulary extension (e.g. extending vocab to 32768 for some models) before finetuning. The project also provides tutorial notebooks (e.g. mistral_finetune_7b.ipynb) to walk through the steps. -
21
Moondream
Tiny vision language model
Moondream is a creative code project and visual experimentation repository that explores generative graphics, aesthetic patterns, and interactive art through code. The project typically showcases procedural visualizations, algorithmic designs, and artistic experiments that push the boundaries of what can be expressed with programming languages and rendering frameworks. While the exact nature can vary by commit or branch, Moondream’s work often blends geometry, color theory, and motion to create immersive visuals that can be interactive, animated, or reactive to input. It serves as both a playground for the author’s artistic curiosity and a resource for other creative coders interested in generative art techniques. The repository may include shaders, canvas/WebGL code, visual demos, and utilities that demonstrate how mathematical functions or noise patterns can be harnessed for compelling visuals. -
22
NVIDIA Isaac GR00T
NVIDIA Isaac GR00T N1.5 is the world's first open foundation model
NVIDIA Isaac‑GR00T N1.5 is an open-source foundation model engineered for generalized humanoid robot reasoning and manipulation skills. It accepts multimodal inputs—such as language and images—and uses a diffusion transformer architecture built upon vision-language encoders, enabling adaptive robot behaviors across diverse environments. It is designed to be customizable via post-training with real or synthetic data. The vision-language model remains frozen during both pretraining and finetuning, preserving language understanding and improving generalization. Streamlined MLP connection between vision encoder and LLM with added layer normalization. -
23
Oasis
Inference script for Oasis 500M
Open-Oasis provides inference code and released weights for Oasis 500M, an interactive world model that generates gameplay frames conditioned on user keyboard input. Instead of rendering a pre-built game world, the system produces the next visual state via a diffusion-transformer approach, effectively “imagining” the world response to your actions in real time. The project focuses on enabling action-conditional frame generation so developers can experiment with interactive, model-generated environments rather than static video generation alone. Because it’s an inference-focused repository, it’s especially useful as a practical reference for running the model, wiring inputs, and producing the autoregressive sequence of gameplay frames. It also serves as a research sandbox for people exploring how far interactive generative models can go with smaller, more accessible checkpoints compared to massive internal systems. -
24
Pearl
A Production-ready Reinforcement Learning AI Agent Library
Pearl is a production-ready reinforcement learning and contextual bandit agent library built for real-world sequential decision making. It is organized around modular components—policy learners, replay buffers, exploration strategies, safety modules, and history summarizers—that snap together to form reliable agents with clear boundaries and strong defaults. The library implements classic and modern algorithms across two regimes: contextual bandits (e.g., LinUCB, LinTS, SquareCB, neural bandits) and fully sequential RL (e.g., DQN, PPO-style policy optimization), with attention to practical concerns like nonstationarity and dynamic action spaces. Tutorials demonstrate end-to-end workflows on OpenAI Gym tasks and contextual-bandit setups derived from tabular datasets, emphasizing reproducibility and clear baselines. Pearl’s design favors clarity and deployability: metrics, logging, and evaluation harnesses are integrated so you can monitor learning, compare agents, and catch regressions. -
25
Perception Models
State-of-the-art Image & Video CLIP, Multimodal Large Language Models
Perception Models is a state-of-the-art framework developed by Facebook Research for advanced image and video perception tasks. It introduces two primary components: the Perception Encoder (PE) for visual feature extraction and the Perception Language Model (PLM) for multimodal decoding and reasoning. The PE module is a family of vision encoders designed to excel in image and video understanding, surpassing models like SigLIP2, InternVideo2, and DINOv2 across multiple benchmarks. Meanwhile, PLM integrates with PE to power vision-language modeling, achieving results competitive with leading multimodal systems such as QwenVL2.5 and InternVL3, all while being fully reproducible with open data. The project supports a wide range of research applications, from visual recognition and dense prediction to fine-grained multimodal understanding. Additionally, it includes several large-scale open datasets for both image and video perception.
