News
ReleasesOVHcloud unveils Olala mini, its first in-house LLMChinaA 9B model beats a 1T model on FinQA, trained with Crusoe Managed RLReleasesThe internal metaphysics of an LLMReleasesMapping Language Model Internal Representations to Physical Laws and Scientific ReasoningResearchCan China keep rogue AI in check? Meet the start-up testing the top modelsFrontierMicrosoft aims to challenge OpenAI, Anthropic with cheaper, specialized AI modelsOpen modelsMicrosoft rolls out new first-party models and updates to agentic AI continuous improvementFrontierMicrosoft unveils AI models for coding, cybersecurity as it takes on Anthropic, OpenAIFrontierGoogle is making it easier to opt out of Gemini AI model training – here’s howFrontierOpenAI Unveils New Astra AI Model After Scrapping Prior ReleaseReleasesOVHcloud unveils Olala mini, its first in-house LLMChinaA 9B model beats a 1T model on FinQA, trained with Crusoe Managed RLReleasesThe internal metaphysics of an LLMReleasesMapping Language Model Internal Representations to Physical Laws and Scientific ReasoningResearchCan China keep rogue AI in check? Meet the start-up testing the top modelsFrontierMicrosoft aims to challenge OpenAI, Anthropic with cheaper, specialized AI modelsOpen modelsMicrosoft rolls out new first-party models and updates to agentic AI continuous improvementFrontierMicrosoft unveils AI models for coding, cybersecurity as it takes on Anthropic, OpenAIFrontierGoogle is making it easier to opt out of Gemini AI model training – here’s howFrontierOpenAI Unveils New Astra AI Model After Scrapping Prior Release
EveryLLM

Fully open

Weights, code and training data all published: OLMo, Pythia, BLOOM. 19 models on EveryLLM so far.

Fully open models publish everything needed to study or rebuild them: the weights, the training data or a precise recipe for it, the training and evaluation code, and often intermediate checkpoints saved during training. They are rarer than open-weights releases because gathering lawful data and documenting it takes work. EleutherAI's Pythia, BigScience's BLOOM, Ai2's OLMo and Switzerland's Apertus are the reference points.

Why release the data

Without the data, outsiders cannot check what a model learned from, test whether benchmark questions leaked into its training, or study how abilities emerge. EleutherAI's Pythia suite (April 2023) released 16 models from 70 million to 12 billion parameters trained on the same public data in the same order, with 154 checkpoints each. Ai2's OLMo (February 2024) released its Dolma dataset, code, logs and checkpoints alongside the weights.

Definitions

The Open Source Initiative published version 1.0 of its Open Source AI Definition on 28 October 2024. It asks for the weights and code under open terms, and for enough detail about the data that a skilled person could build a substantially equivalent system, without always requiring the raw data itself. Apertus, released on 2 September 2025 by EPFL, ETH Zurich and the Swiss National Supercomputing Centre, published its data recipes and code.

Famous fully open models

Still to be written: OLMo (language model).

Further reading

fnDeepSeek 🇨🇳 ChinaDeepSeek A Chinese series of large language models and a free chatbot appGeneral · API only · 2025 GloVe 🇺🇸 United StatesGloVe Unsupervised word embeddings from global word co-occurrence countsResearch · Fully open · 2014 Evo 🇺🇸 United StatesEvo Open genomic language models that read and write DNA, RNA and protein sequencesDomain · Fully open · 2024 T5 🇺🇸 United StatesT5 Encoder-decoder language model family from Google AI using a text-to-text framework.General · Fully open · 2019 imgwavvidGemini 🇺🇸 United StatesGemini Google DeepMind's multimodal LLM family, from Nano to UltraGeneral · API only · 2023 imgwavKimi 🇨🇳 ChinaKimi A Chinese chatbot and large language model family by Moonshot AI.Assistant · API only · 2023 Taiwan-LLM 🇹🇼 TaiwanTaiwan-LLM Open language model for Traditional Chinese in TaiwanRegional · Fully open · 2023 Mamba-2 🇺🇸 United StatesMamba-2 A state-space model architecture for efficient language modellingResearch · Fully open · 2024 Poro 🇫🇮 FinlandPoro Open 34B parameter model for Finnish, English and codeGeneral · Fully open · 2024 Sarvam-Translate 🇮🇳 IndiaSarvam-Translate Document-level translation model for 22 Indian languages.Domain · Fully open Viking 🇫🇮 FinlandViking Open source language model for Nordic languages and codeGeneral · Fully open · 2023 imgLLaVA 🇺🇸 United StatesLLaVA Open-source multimodal chatbot connecting vision encoders to language models.Multimodal · Fully open · 2023 OLMoE 🇺🇸 United StatesOLMoE Open mixture-of-experts language model with 1 billion active parametersGeneral · Fully open · 2024 Megatron-LM 🇺🇸 United StatesMegatron-LM Model-parallel training techniques for transformer language models with billions of parametersResearch · Fully open · 2019 AceGPT 🇨🇳 ChinaAceGPT An Arabic-focused large language model designed for cultural alignment and local values.Regional · Fully open · 2023 S1 🇺🇸 United StatesS1 A reasoning model using test-time scaling and budget forcingReasoning · Fully open · 2025 Eagle and Finch WorldEagle and Finch Efficient recurrent sequence models with matrix statesGeneral · Fully open · 2024 imgMolmo 🇺🇸 United StatesMolmo Open vision-language model family by Allen Institute for AIMultimodal · Fully open · 2024 OpenAssistant 🇩🇪 GermanyOpenAssistant An open source chatbot built by volunteers and LAION.Assistant · Fully open · 2023

The weekly digest

Every Monday: the model of the day, new pages on EveryLLM, and the conferences and anniversaries of the week ahead.