Open Source Llm Model

LiteLLM is an open‑source gateway that unifies access to 100+ LLMs through a single OpenAI‑compatible API, enabling provider fallback, cost tracking, tag‑based budgeting, guardrails, observability, and on‑prem or cloud deployment with a lightweight SDK.

LLM Selector filters open‑source large language models by use case—chatbots, content, code, summarization, research—while presenting benchmarks, training data, architecture, and deployment details. The interface updates regularly to aid researchers, developers, and product managers in data‑driven mo

Falcon is an open‑source LLM family by the Technology Innovation Institute, spanning 0.09‑180 B parameters. It offers efficient Falcon‑H1 series, Arabic variants, multimodal Falcon‑3, and Falcon‑Mamba 7B, all under permissive licenses.

LM Studio runs open‑source large language models locally on Mac (M‑series), Windows, and Linux, enabling private, offline inference. It offers command‑line and headless deployment, server‑side API, SDKs, a model hub, and LM Link for remote model access.

OpenLIT is an open‑source observability platform for large‑language‑model applications, offering distributed tracing, real‑time monitoring, model evaluation, prompt versioning, fleet telemetry, and a zero‑code Kubernetes operator to integrate with major LLM providers and vector databases.

LLM Price Check aggregates LLM API models and provider details into sortable tables and a cost calculator, showing context windows, input/output cost metrics, and quality indicators to help developers and teams evaluate cost–performance tradeoffs.

LLMStack is an open‑source platform that lets developers build AI agents and workflows without coding, supports multiple model providers, imports data from web, PDFs, audio, cloud services, and offers a collaborative React UI with granular permissions.

llmarena.ai offers side-by-side LLM comparisons across major providers, showing specs like context window, output capacity, modality and routing options. Filters and role-based categories help developers, ML engineers, product managers and researchers select suitable models.

Mistral AI offers developers a platform for building cutting-edge generative AI models with a focus on performance and customization. Their models excel in reasoning tasks and benchmarks, providing flexible deployment options across infrastructures.

Llama Family is an extensive AI platform featuring versatile llama models for multiple applications. It promotes open collaboration, democratizing AI access, with notable offerings including the popular Llama open-source model and Atom mega-model for enhanced Chinese language processing capabilitie

VLLM is a high-throughput, memory-efficient inference engine for Large Language Models, enabling faster responses and effective memory management. It supports multi-node configurations for scalability and offers robust documentation for seamless integration into workflows.

LLM Pricing Comparison lets developers and businesses compare token costs, context lengths, and modalities for major large‑language models. An interactive calculator estimates application expenses based on input/output token volumes, helping teams budget AI workloads accurately.

BenchLLM evaluates language‑model applications via API or CLI, running JSON/YAML test suites with automated, interactive, or custom strategies. It supports OpenAI, LangChain, and any API, detecting regressions, generating reports, and visualizing results for continuous QA.

Llama is a local AI tool that enables users to create customizable and efficient language models without relying on cloud-based platforms, available for download on MacOS, Windows, and Linux.

Inception Labs' diffusion-based large language models (dLLMs) offer faster, more efficient, and cost-effective text generation than traditional autoregressive models. With built-in error correction, multimodal support, and structured output control, they excel in function calling and complex data ge

LLM Arena enables users to compare multiple large language models side-by-side, analyzing features like accuracy and capabilities. It supports up to 10 models, facilitating informed decision-making for researchers and developers in selecting the right LLM for their needs.

Unsloth Studio is a no-code web UI enabling local training, running, and exporting of open AI models like Qwen3.5 and NVIDIA Nemotron 3, simplifying experimentation for users without extensive technical expertise.

Llama Tutor is an open‑source AI tutoring platform using Llama 3.1 and Together AI. It creates custom lesson plans and explanations for users across education levels, supports many subjects, and offers real‑time dialogue with adaptive sequencing and instant feedback.

Llama.cpp is an open-source tool for efficient inference of large language models. Run open source LLM models locally everywhere.

Open‑source AI code‑review platform that plugs into GitHub, GitLab, Bitbucket, and Azure DevOps at the pull‑request level. Model‑agnostic, it runs custom rule sets, tracks technical debt, and delivers real‑time metrics without storing source code.

Aleph Alpha offers specialized large language models built on EU infrastructure, trained on domain‑specific data for legal, administrative, industrial, and scientific use. It ensures data sovereignty, compliance, and real‑time workflow integration for secure AI in public, manufacturing, and defense

NOF1 is an AI trading platform linking multiple LLMs to live market execution, model chat logs and a public leaderboard, enabling transparent benchmarking, real‑time P&L, chain‑of‑thought review, strategy-mode analytics and time-series performance charts.

Portkey is an LLMOps platform offering a unified API and model catalog with observability, guardrails, RBAC, audit logs, prompt management, caching, routing and PII redaction to simplify multi-model integration, governance, monitoring, and cost optimization.

Awan LLM offers unlimited token generation with Meta Llama 3.1 8B and 70B models, no censorship or caps, supporting persistent AI assistance, autonomous agents, roleplay, data processing, and code completion, hosted on owned GPUs for continuous use.

LLM Pulse tracks brand visibility and search presence across LLMs (ChatGPT, Perplexity, Google AI), offering prompt tracking and suggestions, citation analysis, visibility scoring and competitor benchmarking, sentiment and response inspection, plus API and reporting exports.

LLMWare AI installs a lightweight client on PCs, providing instant access to 100+ AI models optimized for Intel and Qualcomm hardware. It supports RAG, auto‑tunes weights, runs locally without Wi‑Fi, and offers an admin console for monitoring, scaling, and audit logs.

LLMChat is an AI chat tool that offers a beta version experience with diverse AI models, personalized memory, custom assistant creation, and privacy-focused locally stored conversations. Explore features like plugin integration, tailored preferences, and prompt examples for various tasks.

LM Studio is a local platform for running various large language models like Llama 2 and Mistral. It offers an offline environment, user-friendly interface, and supports multiple operating systems, enhancing privacy and allowing for simultaneous model execution.

Klu accelerates LLM app development by enabling collaborative prompt design, version control, and automated evaluation across multiple providers. It offers unified observability, cost and drift tracking, private infrastructure, continuous monitoring, and integration with 50+ tools for scalable AI de

Ollm.com is a confidential AI gateway providing a single API to route across hundreds of LLM models and providers. It ensures enterprise security with zero data retention, confidential computing, and centralized key management for private, compliant AI workloads.

Latitude offers end‑to‑end observability for LLM deployments, recording inputs, outputs, and context. It enables manual annotations, automated error grouping, continuous evaluation, and prompt optimization with GEPA. OTEL telemetry and SDK integrations support major model providers.

LLMOps Space is a global community for LLM practitioners, offering curated content, discussion forums, event recordings, and resources on production deployment, fine‑tuning, observability, and search optimization, plus networking via Discord and newsletters.

Upstage AI delivers enterprise LLMs and document-processing tools: low-latency and Japan-specific models, PDF/OCR parsing, structured information extraction, centralized search and Q&A with citations, REST/AWS/on‑prem deployment, and team collaboration for review.

Flux LoRA offers a searchable library of low‑rank adaptation models for the FLUX image generation framework. Users can browse, compare, and download models, view usage statistics, and access FAQs and licensing information for compliant deployment.

Reflection 70B is an open‑source 70 B Llama 3.1‑based model that uses real‑time reflection tuning for self‑correction. It outperforms GPT‑4o on MMLU, HumanEval, MATH, IFEval, GSM8K, supporting accurate coding, debugging, and reasoning tasks via API, with a no‑registration web interface.

exllama is a memory-efficient tool for executing Hugging Face transformers with the LLaMA models using quantized weights, enabling high-performance NLP tasks on modern GPUs while minimizing memory usage and supporting various hardware configurations.

xTuring is an open‑source framework that lets developers and researchers build, fine‑tune, and deploy LLMs efficiently. It supports LoRA adapters, INT8 quantization, custom datasets, offers CLI and notebooks, and provides a unified API for multiple backends.

The text-generation-webui is a Gradio-based web UI for Large Language Models, supporting various backends and multiple interface modes. It allows quick model switching, extension integration, and dynamic LoRA loading for custom training.

LLMAPI is a unified OpenAI-compatible LLM gateway offering access to 100+ models across providers, centralized API key management, failover routing, performance and cost analytics, and team-oriented key controls to simplify integration and operations.

gpt-oss playground provides open-weight demos of gpt-oss-120b and 20b for infrastructure testing, distributed and on-device inference, benchmarking, API integration, and reproducible research, with adjustable reasoning levels and visible-reasoning for diagnostics. Demo-only; validate outputs.

llmule is a decentralized network that enables users to run AI models locally, ensuring data privacy. It offers a library of community-shared models, promoting flexibility and collaboration while eliminating reliance on cloud services.

LMQL is a Python‑based language that enables modular, constraint‑driven prompts for large language models. It supports nested queries, type‑enforced outputs, and runtime distribution checks while switching between backends such as llama.cpp, OpenAI, and Hugging Face.

An open-source LLM-based research assistant tool that enables users to converse with research papers.

Open Knowledge Maps is an AI search engine that visualizes scientific literature across disciplines, clustering related papers to reveal topic connections and trends. It supports varied document types, offers high‑quality metadata, multilingual browsing, and open‑source integration.

EvalsOne is an evaluation platform for developers and researchers to assess LLM prompts, RAG, and agents using rule‑based or LLM‑based methods, human judgment, and customizable evaluators. It supports multiple APIs and integrates with major AI frameworks.

Acuration IQ transforms internal and open‑source data into market research, partner discovery, and proposal drafts using a context‑aware LLM. It delivers automated partner matching, data analysis, and instant PDF/Excel/Word/CSV/JSON reports, deployable locally or via LLMaaS.

Velvet, part of Arize, is a developer gateway that links to Arize’s Unified Observability Platform for real‑time AI feature assessment. It supports open‑source LLM tracing, a LiteLLM gateway with 100+ models, fallback, spend tracking, and cloud or on‑premise deployment.

Code Snippets AI indexes full codebases to deliver contextual insights, auto‑generated comments, and precise snippet recommendations. It tracks LLM usage, supports multi‑model chat, offers role‑based collaboration, and integrates with macOS and Windows via API.

FreedomGPT unifies access to 400+ AI models, showing side‑by‑side answers for voting and auto‑selection via leaderboard. It keeps privacy safe, runs on Windows/macOS, and is open‑source for community contribution and collaboration.

LLMWizard offers access to multiple AI models like GPT-4o and DALL-E 3, enabling users to automate tasks across coding, legal work, and content creation. The platform supports real-time comparison of AI responses for diverse insights.