Open Source LLMs
Compare 20 open source llms tools to find the right one for your needs
🔧 Tools
Compare and find the best open source llms for your needs
Meta Llama 3
A family of pretrained and instruction-tuned generative text models from Meta.
Mistral AI
A French company specializing in high-performance, efficient, and accessible large language models.
EleutherAI
A non-profit AI research group focused on open-source AI research and the development of large language models.
Qwen
A series of large language and multimodal models developed by Alibaba Cloud, with many variants distributed as open-weight models.
Google Gemma
A family of lightweight, open models built from the same research and technology used to create the Gemini models.
Falcon
A family of open-source large language models available in various parameter sizes, released under the Apache 2.0 license.
BLOOM
An open-access multilingual large language model created by the BigScience collaborative research workshop.
Vicuna
An open-source chatbot fine-tuned from LLaMA on user-shared conversations.
Databricks Dolly
An open-source, instruction-following large language model from Databricks, licensed for commercial use.
MosaicML MPT
A series of open-source, commercially usable transformers trained from scratch by MosaicML.
Microsoft Phi-3
A family of small, open models from Microsoft with the capability of models 10 times larger.
Microsoft Orca 2
A family of small language models from Microsoft that are taught to use different reasoning strategies for different tasks.
Zephyr
A fine-tuned version of Mistral-7B-v0.1 that is trained on a mix of publicly available, synthetic datasets using Direct Preference Optimization (DPO).
Stability AI StableLM
A family of open-source language models from Stability AI, available in various sizes and designed for a range of text and code generation tasks.
OpenLLaMA
A permissively licensed open-source reproduction of Meta AI's LLaMA large language model.
Cerebras-GPT
A family of seven open-source GPT models from Cerebras Systems, trained to be compute-efficient.
Pythia
A suite of 16 language models from EleutherAI, all trained on the same public data in the same order, designed for scientific research on LLMs.
RedPajama-INCITE
A set of open-source language models from Together AI, trained on the RedPajama dataset, which is an open-source reproduction of the LLaMA training data.
MPT-30B
A 30-billion parameter open-source model from MosaicML, licensed for commercial use and outperforming GPT-3.
DeepSpeed-Chat
A framework from Microsoft's DeepSpeed team for easily and efficiently training high-quality, ChatGPT-style models using RLHF.