Open Source C++ AI Models
Sort By:
C++ AI Models
View 512 business solutionsBrowse free open source C++ AI Models and projects below. Use the toggles on the left to filter open source C++ AI Models by OS, license, language, programming language, and project status.
-
Our Free Plans just got better! | Auth0You asked, we delivered! Auth0 is excited to expand our Free and Paid plans to include more options so you can focus on building, deploying, and scaling applications without having to worry about your security. Auth0 now, thank yourself later.
-
AI-powered service management for IT and enterprise teamsGive your IT, operations, and business teams the ability to deliver exceptional services—without the complexity. Maximize operational efficiency with refreshingly simple, AI-powered Freshservice.
-
1
Piper TTS
A fast, local neural text to speech system
Piper is a fast, local neural text-to-speech (TTS) system developed by the Rhasspy team. Optimized for devices like the Raspberry Pi 4, Piper enables high-quality speech synthesis without relying on cloud services, making it ideal for privacy-conscious applications. It utilizes ONNX models trained with VITS to deliver natural-sounding voices across various languages and accents. Piper is particularly suited for offline voice assistants and embedded systems. -
2
llama.cpp
Port of Facebook's LLaMA model in C/C++
The llama.cpp project enables the inference of Meta's LLaMA model (and other models) in pure C/C++ without requiring a Python runtime. It is designed for efficient and fast model execution, offering easy integration for applications needing LLM-based capabilities. The repository focuses on providing a highly optimized and portable implementation for running large language models directly within C/C++ environments. -
3
stable-diffusion.cpp
Diffusion model(SD,Flux,Wan,Qwen Image,Z-Image,...) inference
stable-diffusion.cpp is a lightweight, high-performance implementation of Stable Diffusion and related generative models written entirely in portable C/C++, designed to run on virtually any device without heavy dependencies. It enables text-to-image and image-to-image generation, supports a growing set of models like SD1.x, SD2.x, SDXL, SD-Turbo, Qwen Image, and more, and is continually updated with support for cutting-edge model variants including video and image editing models. The project is built on the ggml backend, which allows efficient execution on CPUs and GPUs via backends like CUDA, Vulkan, Metal, OpenCL, and SYCL, making it suitable for everything from desktops to mobile devices. It includes options for ControlNet, LoRA models, upscaling via ESRGAN, and advanced sampling techniques, giving developers and users a rich toolkit for creative workflows. -
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. -
AI-generated apps that pass security reviewRetool lets you generate dashboards, admin panels, and workflows directly on your data. Type something like “Build me a revenue dashboard on my Stripe data” and get a working app with security, permissions, and compliance built in from day one. Whether on our cloud or self-hosted, create the internal software your team needs without compromising enterprise standards or control.
-
5
BitNet
Inference framework for 1-bit LLMs
BitNet (bitnet.cpp) is a high-performance inference framework designed to optimize the execution of 1-bit large language models, making them more efficient for edge devices and local deployment. The framework offers significant speedups and energy reductions, achieving up to 6.17x faster performance on x86 CPUs and 70% energy savings, allowing the running of models such as the BitNet b1.58 100B with impressive efficiency. With support for lossless inference and enhanced processing power, BitNet enables faster AI applications while minimizing resource usage. It is a crucial tool for developers looking to implement LLMs on local systems, offering quick execution without sacrificing performance or energy efficiency. -
6
CodeGeeX
CodeGeeX: An Open Multilingual Code Generation Model (KDD 2023)
CodeGeeX is a large-scale multilingual code generation model with 13 billion parameters, trained on 850B tokens across more than 20 programming languages. Developed with MindSpore and later made PyTorch-compatible, it is capable of multilingual code generation, cross-lingual code translation, code completion, summarization, and explanation. It has been benchmarked on HumanEval-X, a multilingual program synthesis benchmark introduced alongside the model, and achieves state-of-the-art performance compared to other open models like InCoder and CodeGen. CodeGeeX also powers IDE plugins for VS Code and JetBrains, offering features like code completion, translation, debugging, and annotation. The model supports Ascend 910 and NVIDIA GPUs, with optimizations like quantization and FasterTransformer acceleration for faster inference. -
7
Step 3.5 Flash
Fast, Sharp & Reliable Agentic Intelligence
Step 3.5 Flash is a cutting-edge, open-source large language model developed by StepFun-AI that pushes the frontier of efficient reasoning and “agentic” intelligence in a way that makes powerful AI accessible beyond proprietary black boxes. Unlike dense models that activate all their parameters for every token, Step 3.5 Flash uses a sparse Mixture-of-Experts (MoE) architecture that selectively engages only about 11 billion of its roughly 196 billion total parameters per token, delivering high-quality reasoning and interaction at far lower compute cost and latency than traditional large models. Its design targets deep reasoning, long-context handling, coding, and real-time responsiveness, making it suitable for building autonomous agents, advanced assistants, and long-chain cognitive workflows without sacrificing performance. -
8
Alpaca.cpp
Locally run an Instruction-Tuned Chat-Style LLM
Run a fast ChatGPT-like model locally on your device. This combines the LLaMA foundation model with an open reproduction of Stanford Alpaca a fine-tuning of the base model to obey instructions (akin to the RLHF used to train ChatGPT) and a set of modifications to llama.cpp to add a chat interface. Download the zip file corresponding to your operating system from the latest release. The weights are based on the published fine-tunes from alpaca-lora, converted back into a PyTorch checkpoint with a modified script and then quantized with llama.cpp the regular way. -
9
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. -
Find Hidden Risks in Windows Task SchedulerWindows Task Scheduler might be hiding critical failures. Download the free JAMS diagnostic tool to uncover problems before they impact production—get a color-coded risk report with clear remediation steps in minutes.
-
10
ChatGLM.cpp
C++ implementation of ChatGLM-6B & ChatGLM2-6B & ChatGLM3 & GLM4(V)
ChatGLM.cpp is a C++ implementation of the ChatGLM-6B model, enabling efficient local inference without requiring a Python environment. It is optimized for running on consumer hardware. -
11
FlashMLA
FlashMLA: Efficient Multi-head Latent Attention Kernels
FlashMLA is a high-performance decoding kernel library designed especially for Multi-Head Latent Attention (MLA) workloads, targeting NVIDIA Hopper GPU architectures. It provides optimized kernels for MLA decoding, including support for variable-length sequences, helping reduce latency and increase throughput in model inference systems using that attention style. The library supports both BF16 and FP16 data types, and includes a paged KV cache implementation with a block size of 64 to efficiently manage memory during decoding. On very compute-bound settings, it can reach up to ~660 TFLOPS on H800 SXM5 hardware, while in memory-bound configurations it can push memory throughput to ~3000 GB/s. The team regularly updates it with performance improvements; for example, a 2025 update claims 5 % to 15 % gains on compute-bound workloads while maintaining API compatibility. -
12
fairseq2
FAIR Sequence Modeling Toolkit 2
fairseq2 is a modern, modular sequence modeling framework developed by Meta AI Research as a complete redesign of the original fairseq library. Built from the ground up for scalability, composability, and research flexibility, fairseq2 supports a broad range of language, speech, and multimodal content generation tasks, including instruction fine-tuning, reinforcement learning from human feedback (RLHF), and large-scale multilingual modeling. Unlike the original fairseq—which evolved into a large, monolithic codebase—fairseq2 introduces a clean, plugin-oriented architecture designed for long-term maintainability and rapid experimentation. It supports multi-GPU and multi-node distributed training using DDP, FSDP, and tensor parallelism, capable of scaling up to 70B+ parameter models. The framework integrates seamlessly with PyTorch 2.x features such as torch.compile, Fully Sharded Data Parallel (FSDP), and modern configuration management. -
13
rwkv.cpp
INT4/INT5/INT8 and FP16 inference on CPU for RWKV language model
Besides the usual FP32, it supports FP16, quantized INT4, INT5 and INT8 inference. This project is focused on CPU, but cuBLAS is also supported. RWKV is a novel large language model architecture, with the largest model in the family having 14B parameters. In contrast to Transformer with O(n^2) attention, RWKV requires only state from the previous step to calculate logits. This makes RWKV very CPU-friendly on large context lengths. -
14
DeepSDF
Learning Continuous Signed Distance Functions for Shape Representation
DeepSDF is a deep learning framework for continuous 3D shape representation using Signed Distance Functions (SDFs), as presented in the CVPR 2019 paper DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation by Park et al. The framework learns a continuous implicit function that maps 3D coordinates to their corresponding signed distances from object surfaces, allowing compact, high-fidelity shape modeling. Unlike traditional discrete voxel grids or meshes, DeepSDF encodes shapes as continuous neural representations that can be smoothly interpolated and used for reconstruction, generation, and analysis. The repository provides complete tooling for preprocessing mesh datasets (e.g., ShapeNet), training DeepSDF models, reconstructing meshes from learned latent codes, and quantitatively evaluating results with metrics such as Chamfer Distance and Earth Mover’s Distance. -
15
MuJoCo MPC
Real-time behaviour synthesis with MuJoCo, using Predictive Control
MuJoCo MPC (MJPC) is an advanced interactive framework for real-time model predictive control (MPC) built on top of the MuJoCo physics engine, developed by Google DeepMind. It allows researchers and roboticists to design, visualize, and execute complex control tasks for simulated or real robotic systems. MJPC integrates a high-performance GUI and multiple predictive control algorithms, including iLQG, gradient descent, and Predictive Sampling — a competitive, derivative-free method that achieves robust real-time control. The system supports multi-shooting optimization, enabling precise motion planning across diverse domains like quadruped locomotion, humanoid tracking, and dexterous manipulation. In addition to its C++ core, MJPC includes an experimental Python API, enabling integration with custom models and MuJoCo tasks for flexible scripting and experimentation. -
16
Proximus for Ryzen AI
Runtime extension of Proximus enabling Deployment on AMD Ryzen™ AI
This project extends the Proximus development environment to support deployment of AI workloads on next-generation AMD Ryzen™ AI processors, such as the Ryzen™ AI 7 PRO 7840U featured in the Lenovo ThinkPad T14s Gen 4 ,one of the first true AI PCs with an onboard Neural Processing Unit (NPU) capable of 16 TOPS (trillion operations per second). Originally designed for use with Windows 11 Pro, this runtime was further enhanced to work under Linux environments, allowing developers and researchers to fully utilize the AMD AI Engine across both platforms. This cross-platform support is a major innovation, enabling AI workload portability, integration into CI environments, and deployment into Linux-based research and production pipelines. -
17
StarSpace
Learning embeddings for classification, retrieval and ranking
StarSpace is a general-purpose embedding-based learning framework that trains embeddings for entities (words, sentences, users, items) under various supervision signals (classification, ranking, matching). Instead of focusing on one task, StarSpace supports multi-task and multi-domain setups—for instance, you can train embeddings so that textual queries match item descriptions, sentences map to labels, or users align with liked items in the same embedding space. The training objective is contrastive: for a given query embedding, positive and negative examples are sampled and the model is optimized to score positive higher than negatives. The library supports a variety of tasks (text classification, nearest-neighbor search, recommendation, entity linking) with simple configuration. It includes efficient batching, negative sampling strategies, and on-the-fly embedding updates. -
18
VMZ (Video Model Zoo)
VMZ: Model Zoo for Video Modeling
The codebase was designed to help researchers and practitioners quickly reproduce FAIR’s results and leverage robust pre-trained backbones for downstream tasks. It also integrates Gradient Blending, an audio-visual modeling method that fuses modalities effectively (available in the Caffe2 implementation). Although VMZ is now archived and no longer actively maintained, it remains a valuable reference for understanding early large-scale video model training, transfer learning, and multimodal integration strategies that influenced modern architectures like SlowFast and X3D.
- Previous
- You're on page 1
- Next
