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

Dense decoder transformers

The GPT design: one stack of transformer layers predicting the next token. 308 models on EveryLLM so far.

The dense decoder transformer is the design behind GPT and most chatbots. It is a single stack of identical transformer layers that reads the tokens so far and predicts the next one, with a mask that stops each position from looking ahead. Dense means every parameter is used for every token, unlike in a mixture of experts. GPT-3, PaLM, Llama 3, Chinchilla, Gemma, Phi and OLMo are dense decoders.

Inside each layer

Each layer has two parts. Self-attention lets every token weigh every earlier token and gather what it needs; a feed-forward network then transforms each token's vector on its own. The transformer was introduced by Google researchers in the June 2017 paper Attention Is All You Need, for translation, and OpenAI's GPT-1 (2018) kept only its decoder half. Llama 3.1 405B, released in July 2024, stacks 126 such layers.

Why it won

A decoder trains on any text without labels, because the next token is always the answer to predict, and it scales smoothly: scaling laws published by OpenAI in 2020 and DeepMind in 2022 showed the error falling predictably with more parameters, data and compute. Its weak point is cost. Attention grows with the square of the context length, and every parameter must be read for every token, which is why mixtures of experts became popular.

Famous dense decoder models

Still to be written: OLMo (language model).

Further reading

Jurassic-2 🇮🇱 IsraelJurassic-2 AI21 Labs' second-generation family of large language models in three sizesGeneral · API only · 2023 Mixtral 8x7B 🇫🇷 FranceMixtral 8x7B Sparse mixture-of-experts language model with open weightsGeneral · Open weights · 2023 Mistral Saba 🇫🇷 FranceMistral Saba A 24B regional language model for Arabic and South Asian languagesRegional · API only · 2025 Mistral Large 🇫🇷 FranceMistral Large Mistral AI's flagship multilingual text model, released in 2024 and now deprecated.General · API only · 2024 Nemotron-4 340B 🇺🇸 United StatesNemotron-4 340B NVIDIA's 340B open-access model family for chat and synthetic data generationGeneral · Conditional licence · 2024 imgMistral Medium 3 🇫🇷 FranceMistral Medium 3 A mid-size language model aimed at enterprise coding and multimodal workGeneral · API only · 2025 wavVoxtral 🇫🇷 FranceVoxtral Open audio chat models that transcribe, answer questions and summarise speechMultimodal · Open weights · 2025 fnMiniMax-M2.7 🇨🇳 ChinaMiniMax-M2.7 Open-weight model for coding and agent tasksCode · Open weights DeepSeek-V2 🇨🇳 ChinaDeepSeek-V2 Efficient mixture-of-experts language model with 236 billion parametersGeneral · Open weights · 2024 fnGPT-6 🇺🇸 United StatesGPT-6 OpenAI family of large language models released in late 2026.General · API only · 2026 fnDevin 🇺🇸 United StatesDevin Autonomous software engineering agent by Cognition LabsCode · API only fnClaude Opus 4 🇺🇸 United StatesClaude Opus 4 High-capability reasoning model from Anthropic released in May 2025.Reasoning · API only · 2025 fnClaude Sonnet 4 🇺🇸 United StatesClaude Sonnet 4 Mid-tier reasoning model from Anthropic released in May 2025Reasoning · API only · 2025 imgwavChatGPT 🇺🇸 United StatesChatGPT Generative AI chatbot by OpenAIAssistant · API only · 2022

The weekly digest

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