Open Source BSD Large Language Models (LLM)
Sort By:
Large Language Models (LLM) for BSD
Browse free open source Large Language Models (LLM) and projects for BSD below. Use the toggles on the left to filter open source Large Language Models (LLM) 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.
-
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
1
GPT4All
Run Local LLMs on Any Device. Open-source
GPT4All is an open-source project that allows users to run large language models (LLMs) locally on their desktops or laptops, eliminating the need for API calls or GPUs. The software provides a simple, user-friendly application that can be downloaded and run on various platforms, including Windows, macOS, and Ubuntu, without requiring specialized hardware. It integrates with the llama.cpp implementation and supports multiple LLMs, allowing users to interact with AI models privately. This project also supports Python integrations for easy automation and customization. GPT4All is ideal for individuals and businesses seeking private, offline access to powerful LLMs. -
2
GLM-5
From Vibe Coding to Agentic Engineering
GLM-5 is a next-generation open-source large language model (LLM) developed by the Z .ai team under the zai-org organization that pushes the boundaries of reasoning, coding, and long-horizon agentic intelligence. Building on earlier GLM series models, GLM-5 dramatically scales the parameter count (to roughly 744 billion) and expands pre-training data to significantly improve performance on complex tasks such as multi-step reasoning, software engineering workflows, and agent orchestration compared to its predecessors like GLM-4.5. It incorporates innovations like DeepSeek Sparse Attention (DSA) to preserve massive context windows while reducing deployment costs and supporting long context processing, which is crucial for detailed plans and agent tasks. -
3
Hands-On Large Language Models
Official code repo for the O'Reilly Book
Hands-On-Large-Language-Models is the official GitHub code repository accompanying the practical technical book Hands-On Large Language Models authored by Jay Alammar and Maarten Grootendorst, providing a comprehensive collection of example notebooks, code labs, and supporting materials that illustrate the core concepts and real-world applications of large language models. The repository is structured into chapters that align with the educational progression of the book — covering everything from foundational topics like tokens, embeddings, and transformer architecture to advanced techniques such as prompt engineering, semantic search, retrieval-augmented generation (RAG), multimodal LLMs, and fine-tuning. Each chapter contains executable Jupyter notebooks that are designed to be run in environments like Google Colab, making it easy for learners to experiment interactively with models, visualize attention patterns, implement classification and generation tasks. -
4
BruteForceAI
Advanced LLM-powered brute-force tool combining AI intelligence
BruteForceAI is an open-source security testing tool that applies large language models to the analysis of login forms and authentication flows in web applications. At a high level, the project uses AI to inspect HTML content, identify the relevant form elements, and automate selector discovery so that a tester does not need to hand-map every field before evaluation. It combines that analysis layer with automated credential testing workflows, framing itself as a more adaptive alternative to older brute-force tooling that depends heavily on manual configuration. The repository emphasizes features such as threaded execution, logging, and notification integrations, which position it as an automation-oriented project for controlled security assessment environments. From a software design perspective, its distinguishing idea is the use of language models as a front-end analysis layer that interprets a target page before the rest of the workflow proceeds. -
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.
-
5
WeChatMsg
Project aimed at extracting, exporting, and analyzing chat records
WeChatMsg repository hosts an open-source project aimed at extracting, exporting, and analyzing chat records from the WeChat messaging platform. It provides tools that read local WeChat database files and allow users to convert chat data into readable formats such as HTML, Word, and CSV, making it possible to inspect conversations outside the mobile app environment. Beyond simple export, the project includes mechanisms for analyzing chat histories and generating annual reports or visual summaries about messaging trends, interaction patterns, and more. The original README communicates a guiding philosophy about owning personal data and using it responsibly to train personalized AI agents or preserve memories. Although the repository has seen periods of inactivity and may not receive frequent updates, its widespread use indicates community interest in preserving chat logs and understanding conversation data outside of the WeChat interface. -
6
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. -
7
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. -
8
LLPlayer
The media player for language learning, with dual subtitles
LLPlayer is an open-source media player designed specifically for language learning through video content. Unlike traditional media players, the application focuses on advanced subtitle-related features that help learners understand and interact with foreign language media more effectively. The player supports dual subtitles so users can simultaneously view text in both the original language and their native language while watching videos. It can also automatically generate subtitles in real time using speech-to-text systems such as Whisper, allowing subtitles to be created even when none are available. Real-time translation capabilities enable subtitles to be translated using multiple translation engines and language models. Additional tools such as instant word lookup, contextual translation, and subtitle search allow learners to interact with the text while watching videos. -
9
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. -
Train ML Models With SQL You Already KnowBuild and deploy ML models using familiar SQL. Automate data prep with built-in Gemini. Query 1 TB and store 10 GB free monthly.
-
10
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. -
11
MiroFish
A Simple and Universal Swarm Intelligence Engine
MiroFish is a next-generation artificial intelligence prediction engine that leverages multi-agent technology and swarm-intelligence simulation to model, simulate, and forecast complex real-world scenarios. The system extracts “seed” information from sources such as breaking news, policy documents, and market signals to construct a high-fidelity digital parallel world populated by thousands of virtual agents with independent memory and behavior rules. Users can inject variables or conditions into this simulated environment from a “god’s eye view,” enabling iterative prediction of future trends under different assumptions, which can be useful for decision support, scenario planning, or creative exploration. The engine includes both backend and frontend components, with configuration and deployment instructions for local and containerized setups, and is designed to produce detailed predictive reports based on interactions and emergent patterns within the simulated world. -
12
GLM-4.7
Advanced language and coding AI model
GLM-4.7 is an advanced agent-oriented large language model designed as a high-performance coding and reasoning partner. It delivers significant gains over GLM-4.6 in multilingual agentic coding, terminal-based workflows, and real-world developer benchmarks such as SWE-bench and Terminal Bench 2.0. The model introduces stronger “thinking before acting” behavior, improving stability and accuracy in complex agent frameworks like Claude Code, Cline, and Roo Code. GLM-4.7 also advances “vibe coding,” producing cleaner, more modern UIs, better-structured webpages, and visually improved slide layouts. Its tool-use capabilities are substantially enhanced, with notable improvements in browsing, search, and tool-integrated reasoning tasks. Overall, GLM-4.7 shows broad performance upgrades across coding, reasoning, chat, creative writing, and role-play scenarios. -
13
Kimi K2
Kimi K2 is the large language model series developed by Moonshot AI
Kimi K2 is Moonshot AI’s advanced open-source large language model built on a scalable Mixture-of-Experts (MoE) architecture that combines a trillion total parameters with a subset of ~32 billion active parameters to deliver powerful and efficient performance on diverse tasks. It was trained on an enormous corpus of over 15.5 trillion tokens to push frontier capabilities in coding, reasoning, and general agentic tasks while addressing training stability through novel optimizer and architecture design strategies. The model family includes variants like a foundational base model that researchers can fine-tune for specific use cases and an instruct-optimized variant primed for general-purpose chat and agent-style interactions, offering flexibility for both experimentation and deployment. With its high-dimensional attention mechanisms and expert routing, Kimi-K2 excels across benchmarks in live coding, math reasoning, and problem solving. -
14
FreeLLMAPI
OpenAI-compatible proxy that aggregates free-tier keys from ~14 AI
FreeLLMAPI is an OpenAI-compatible proxy that aggregates free-tier API keys from multiple AI providers into one unified endpoint. It is designed for personal experimentation, testing, and lightweight development workflows where users want to route requests through several providers without rewriting client code for each one. The project can automatically fail over between configured providers when one is unavailable or exhausted. Its OpenAI-compatible design makes it easier to use with existing tools, SDKs, and applications that already expect that API shape. It is not positioned as an enterprise-grade service or a way to bypass provider terms, but as a local coordination layer for personally owned free-tier credentials. freellmapi is useful for developers who want a practical testing proxy for comparing models, managing limits, and improving request continuity. -
15
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. -
16
LLaMA 3
The official Meta Llama 3 GitHub site
This repository is the former home for Llama 3 model artifacts and getting-started code, covering pre-trained and instruction-tuned variants across multiple parameter sizes. It introduced the public packaging of weights, licenses, and quickstart examples that helped developers fine-tune or run the models locally and on common serving stacks. As the Llama stack evolved, Meta consolidated repositories and marked this one deprecated, pointing users to newer, centralized hubs for models, utilities, and docs. Even as a deprecated repo, it documents the transition path and preserves references that clarify how Llama 3 releases map into the current ecosystem. Practically, it functioned as a bridge between Llama 2 and later Llama releases by standardizing distribution and starter code for inference and fine-tuning. Teams still treat it as historical reference material for version lineage and migration notes. -
17
Clippy
Clippy, now with some AI
Clippy is an open-source desktop assistant that allows users to run modern large language models locally while presenting them through a nostalgic interface inspired by Microsoft’s classic Clippy assistant from the 1990s. The project serves as both a playful homage to the early days of personal computing and a practical demonstration of local AI inference. Clippy integrates with the llama.cpp runtime to run models directly on a user’s computer without requiring cloud-based AI services. It supports models in the GGUF format, which allows it to run many publicly available open-source LLMs efficiently on consumer hardware. Users interact with the system through a simple animated assistant interface that can answer questions, generate text, and perform conversational tasks. The application includes one-click installation support for several popular models such as Meta’s Llama, Google’s Gemma, and other open models. -
18
MLC LLM
Universal LLM Deployment Engine with ML Compilation
MLC LLM is a machine learning compiler and deployment framework designed to enable efficient execution of large language models across a wide range of hardware platforms. The project focuses on compiling models into optimized runtimes that can run natively on devices such as GPUs, mobile processors, browsers, and edge hardware. By leveraging machine learning compilation techniques, mlc-llm produces high-performance inference engines that maintain consistent APIs across platforms. The system supports deployment on environments including Linux, macOS, Windows, iOS, Android, and web browsers while utilizing different acceleration technologies such as CUDA, Vulkan, Metal, and WebGPU. It also provides OpenAI-compatible APIs that allow developers to integrate locally deployed models into existing AI applications without major code changes. -
19
AxonHub
Use any SDK to call 100+ LLMs
AxonHub is an open-source AI gateway platform designed to simplify the process of integrating and switching between different large language model providers. The system acts as a compatibility layer that allows developers to use the same SDK interface while routing requests to various AI services behind the scenes. Instead of rewriting code when switching providers such as OpenAI or Anthropic, developers can simply change configuration settings within the gateway. AxonHub translates requests from one provider’s API format into another, enabling seamless interoperability across different AI platforms. The system also provides infrastructure features such as request routing, failover mechanisms, load balancing, and cost management for AI applications. This architecture makes it easier to experiment with multiple models and manage production deployments that rely on several providers simultaneously. -
20
llmfit
157 models, 30 providers, one command to find what runs on hardware
llmfit is a terminal-based utility that helps developers determine which large language models can realistically run on their local hardware by analyzing system resources and model requirements. The tool automatically detects CPU, RAM, GPU, and VRAM specifications, then ranks available models based on performance factors such as speed, quality, and memory fit. It provides both an interactive terminal user interface and a traditional CLI mode, enabling flexible workflows for different user preferences. llmfit also supports advanced configurations including multi-GPU setups, mixture-of-experts architectures, and dynamic quantization recommendations. By presenting clear performance estimates and compatibility guidance, the project reduces the trial-and-error typically involved in local LLM experimentation. Overall, llmfit serves as a practical decision assistant for developers who want to run language models efficiently on their own machines. -
21
Token-Oriented Object Notation
Token-Oriented Object Notation (TOON)
Token-Oriented Object Notation is an open specification and toolkit for a data serialization format called Token-Oriented Object Notation (TOON), designed specifically to optimize how structured data is passed to large language models. The format aims to reduce token overhead compared with traditional formats like JSON while remaining human-readable and structurally expressive. TOON represents the same data model as JSON but removes unnecessary syntax such as braces and quotes, relying instead on indentation and structured tokens to represent objects and arrays. This design allows prompts containing structured data to use significantly fewer tokens, which can reduce inference costs and improve efficiency in LLM applications. The project includes a formal specification, encoding rules, and reference implementations that developers can use to serialize and parse TOON data in their applications. -
22
slime LLM
slime is an LLM post-training framework for RL Scaling
slime is an open-source large language model (LLM) post-training framework developed to support reinforcement learning (RL)-based scaling and high-performance training workflows for advanced LLMs, blending training and rollout modules into an extensible system. It offers a flexible architecture that connects high-throughput training (e.g., via Megatron-LM) with a customizable data generation pipeline, enabling researchers and engineers to iterate on new RL training paradigms effectively. The framework is designed to support a wide range of training modes, allowing both synchronous and asynchronous RL workflows and programmable rollout interfaces that simplify experimentation with custom environments and reward signals. Because it integrates tightly with SGLang and other training engines, slime can improve scalability and efficiency while providing maintainability and adaptability for developing new models and training algorithms. -
23
AirLLM
AirLLM 70B inference with single 4GB GPU
AirLLM is an open source Python library that enables extremely large language models to run on consumer hardware with very limited GPU memory. The project addresses one of the main barriers to local LLM experimentation by introducing a memory-efficient inference technique that loads model layers sequentially rather than storing the entire model in GPU memory. This layer-wise inference approach allows models with tens of billions of parameters to run on devices with only a few gigabytes of VRAM. AirLLM preprocesses model weights so that each transformer layer can be loaded independently during computation, reducing the memory footprint while still performing full inference. As a result, developers can experiment with models that previously required specialized high-end GPUs. -
24
AudioMuse-AI
AudioMuse-AI is an Open Source Dockerized environment
AudioMuse-AI is an open-source system designed to automatically generate playlists and analyze music libraries using artificial intelligence and audio signal processing techniques. The platform runs locally in a Dockerized environment and performs detailed sonic analysis on audio files to understand characteristics such as tempo, mood, and acoustic similarity. By analyzing the underlying audio content rather than relying on external metadata services, the system can organize large personal music libraries and generate curated playlists for different moods or listening contexts. AudioMuse-AI integrates with several popular self-hosted music servers including Jellyfin, Navidrome, and Emby, allowing users to extend existing media servers with advanced AI-powered recommendation capabilities. The system uses machine learning and audio analysis tools such as Librosa and ONNX models to extract features directly from audio tracks. -
25
Heretic
Fully automatic censorship removal for language models
Heretic is an open-source Python tool that automatically removes the built-in censorship or “safety alignment” from transformer-based language models so they respond to a broader range of prompts with fewer refusals. It works by applying directional ablation techniques and a parameter optimization strategy to adjust internal model behaviors without expensive post-training or altering the core capabilities. Designed for researchers and advanced users, Heretic makes it possible to study and experiment with uncensored model responses in a reproducible, automated way. The project can decensor many popular dense and some mixture-of-experts (MoE) models, supporting workflows that would otherwise require manual tuning. Beyond simple decensoring, Heretic includes research-oriented options for analyzing model internals and interpretability data.