Open Source LLMs - Directory w/ AI Reviews
Open-source LLMs have democratized access to capable language models that can run on private infrastructure without API fees or data sharing. Llama 3 and Gemma 2 from Meta and Google have set new benchmarks for open-weight capability. Ollama makes running these models locally as simple as a single command, while Together AI and Groq provide cloud inference for teams that need open models at scale. Hugging Face hosts the open-source model ecosystem, and vLLM provides the high-throughput serving engine that powers many deployments.
1
4.9
New
Hugging Face
Freemium
Free Plan
API
Open Source
Enterprise
Hugging Face is the primary distribution platform for open-source large language models, hosting models from Meta (LLaMA), Mistral, Google, Microsoft, and thousands of community contributors. Its Transformers library provides a unified interface for loading, running, and fine-tuning open-source LLMs
2
4.8
New
Ollama
Free
Free Plan
Open Source
Ollama is the most popular tool for running open-source LLMs locally, providing easy access to models like LLaMA, Mistral, Gemma, DeepSeek, and dozens of others. It handles model downloading, quantization, and hardware optimization, making open-source language models accessible to anyone with a pers
3
4.8
New
Together AI
Paid
API
Enterprise
Together AI specializes in hosting and serving open-source language models, providing fast and affordable API access to models from Meta, Mistral, DeepSeek, and other open-source providers. Its platform makes it easy to run, compare, and integrate open-source LLMs without managing GPU infrastructure
4
4.8
New
vLLM
Free
Free Plan
API
Open Source
vLLM is a high-throughput, memory-efficient inference engine for serving large language models. Developed at UC Berkeley, it uses PagedAttention to dramatically reduce memory waste and increase serving speed, making it one of the fastest open-source LLM serving frameworks available. vLLM supports a
5
4.7
New
Text Generation Web UI
Free
Free Plan
API
Open Source
Text Generation Web UI (commonly called oobabooga) is a popular open-source Gradio-based interface for running large language models locally. It supports a wide range of model loaders including GPTQ, GGUF, AWQ, and ExLlamaV2, and provides features like chat mode, notebook mode, extensions, and LoRA
6
4.7
New
LocalAI
Free
Free Plan
API
Open Source
LocalAI is a free, open-source alternative to OpenAI's API that runs entirely on consumer hardware without requiring a GPU. It provides an OpenAI-compatible REST API for running LLMs, image generation, audio transcription, and embeddings locally. LocalAI supports dozens of model families and is desi
7
4.6
New
Jan
Free
Free Plan
API
Open Source
Jan is an open-source desktop application for running large language models locally on Mac, Windows, and Linux. It provides a clean ChatGPT-like interface for offline AI conversations, supports popular model formats like GGUF, and includes a built-in model hub for downloading models. Jan emphasizes
8
4.5
New
Groq
Freemium
Free Plan
API
Enterprise
Groq serves popular open-source language models including LLaMA, Mistral, Mixtral, and Gemma through its ultra-fast inference platform. Its LPU hardware enables these open-source models to run at dramatically faster speeds than traditional GPU infrastructure, making them more practical for real-time
9
4.5
New
Replicate
Paid
API
Enterprise
Replicate hosts and serves many popular open-source language models, enabling developers to run models like LLaMA, Mistral, and other community models through a simple API without managing GPU infrastructure. Its platform makes open-source LLMs accessible to developers who lack their own GPU resourc
10
4.3
New
Whisper
Free
Free Plan
API
Open Source
While technically a speech model rather than a language model, Whisper is one of OpenAI's most significant open-source AI releases under the MIT license. Its open availability has enabled an entire ecosystem of derivative tools and optimized implementations, making it a cornerstone of the open-sourc