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

imgMiniCPM-V 🇨🇳 ChinaMiniCPM-V Efficient multimodal model for mobile devicesMultimodal · Open weights · 2024 Sarashina2 🇯🇵 JapanSarashina2 Open-weight Japanese and English language models by SB IntuitionsGeneral · Open weights fnGLM-4.6 🇨🇳 ChinaGLM-4.6 A large language model with a 200K token context window.General · API only RakutenAI-7B 🇯🇵 JapanRakutenAI-7B Japanese-focused open language model based on MistralGeneral · Open weights · 2024 imgKimi k1.5 🇨🇳 ChinaKimi k1.5 Multimodal LLM trained with reinforcement learning for reasoningReasoning · Research only · 2025 PLLuM 🇵🇱 PolandPLLuM Polish-focused large language model familyGeneral · Open weights · 2024 Claude 1 🇺🇸 United StatesClaude 1 Anthropic's first AI assistant model, offered in two versions via chat and API.Assistant · API only Pythia 🇺🇸 United StatesPythia A suite of 16 models for interpretability research.Research · Open weights · 2023 Falcon 3 🇦🇪 United Arab EmiratesFalcon 3 Open foundation models from 1B to 10B parameters by TIIGeneral · Open weights · 2024 ULMFiT WorldULMFiT Transfer learning method for NLP text classification tasksResearch · Open weights · 2018 INTELLECT-1 WorldINTELLECT-1 A 10 billion parameter model trained by a global community.General · Open weights · 2024 ChatGLM-6B 🇨🇳 ChinaChatGLM-6B Open bilingual dialogue model with 6.2 billion parametersAssistant · Open weights fnCodestral 🇫🇷 FranceCodestral Mistral AI's 22B open-weight model built for code generation across 80+ languagesCode · Conditional licence fnWebGPT 🇺🇸 United StatesWebGPT A GPT-3 model fine-tuned to answer questions while browsing the webGeneral · Research only · 2021 Grok-1.5 🇺🇸 United StatesGrok-1.5 xAI's long-context Grok model with stronger reasoning and coding skillsGeneral · API only · 2024 Megatron-LM 🇺🇸 United StatesMegatron-LM Model-parallel training techniques for transformer language models with billions of parametersResearch · Fully open · 2019 Falcon2-11B 🇦🇪 United Arab EmiratesFalcon2-11B An 11 billion parameter causal decoder model by TII.General · Open weights · 2024 Phi-4-reasoning 🇺🇸 United StatesPhi-4-reasoning A 14B open-weight reasoning model fine-tuned from Phi-4Reasoning · Open weights · 2025 imgwavPhi-4-multimodal 🇺🇸 United StatesPhi-4-multimodal A small open model that reads text, images and audio and replies in textMultimodal · Open weights · 2025 Phi-4-mini 🇺🇸 United StatesPhi-4-mini A 3.8B-parameter compact language model from Microsoft for reasoning, maths and codeSmall · Open weights · 2025 imgPhi-3 🇺🇸 United StatesPhi-3 Small Microsoft language models built to run well on phones and laptops.Small · Open weights · 2024 Phi-1 🇺🇸 United StatesPhi-1 A small Microsoft model specialised for basic Python codingCode · Open weights · 2023 imgChameleon WorldChameleon Early-fusion models that read and write images and text in one streamMultimodal · Research only · 2024 InstructGPT 🇺🇸 United StatesInstructGPT GPT-3 models fine-tuned with human feedback to follow instructionsGeneral · API only · 2022 Jurassic-2 🇮🇱 IsraelJurassic-2 AI21 Labs' second-generation family of large language models in three sizesGeneral · API only · 2023 Orca 2 🇺🇸 United StatesOrca 2 A small LLaMA-2-based model trained on synthetic data to reason.Small · Conditional licence · 2023 fnBlenderBot 3 WorldBlenderBot 3 A 175B open-domain chatbot with internet access and long-term memoryGeneral · Open weights · 2022 Llama Guard WorldLlama Guard A Llama 2 based model that classifies prompts and replies for safety risksDomain · Open weights · 2023 Code Llama 🇺🇸 United StatesCode Llama Meta's code-specialised family of Llama 2 models in four sizesCode · Conditional licence · 2023 Phi-4 🇺🇸 United StatesPhi-4 A 14B Microsoft Research model trained heavily on synthetic data for reasoning.General · Open weights · 2024 Phi-2 🇺🇸 United StatesPhi-2 A 2.7 billion parameter Microsoft research model for QA, chat and codeResearch · Open weights imgLlama 3.2 🇺🇸 United StatesLlama 3.2 Small text models and vision models from Meta for edge devices and image tasksMultimodal · Open weights · 2024 fnLlama 3.1 405B 🇺🇸 United StatesLlama 3.1 405B Meta's largest openly available language model, released in 2024General · Conditional licence · 2024 Gopher 🇬🇧 United KingdomGopher A 280 billion parameter Transformer language model from DeepMind, studied for how scale changes ability.Research · Research only · 2021 DeepSeek LLM 67B 🇨🇳 ChinaDeepSeek LLM 67B A 67-billion-parameter open-source model trained on English and Chinese text.General · Conditional licence · 2024 Llama 2 🇺🇸 United StatesLlama 2 Meta's open family of pretrained and chat-tuned language models, 7B to 70BGeneral · Open weights · 2023 imgMM1 WorldMM1 A family of multimodal language models up to 30B parameters, dense and MoE.Multimodal · Research only · 2024 Nemotron-4-Mini-Hindi-4B-Instr 🇺🇸 United StatesNemotron-4-Mini-Hindi-4B-Instruct A small Hindi-focused chat model from NVIDIA, tuned for Indian-context answersSmall · Open weights · 2024 Minerva 🇺🇸 United StatesMinerva A language model trained further on technical content to solve maths and science problemsResearch · Research only · 2022 OpenHathi 🇮🇳 IndiaOpenHathi A 7 billion parameter language model for Hindi and English.General · Open weights imgfnGLM-4 🇨🇳 ChinaGLM-4 Multilingual large language model series by Zhipu AIGeneral · Open weights · 2024 Med-PaLM 2 🇺🇸 United StatesMed-PaLM 2 Google's medical question-answering model built on PaLM 2Domain · Research only · 2023 Tamil-LLaMA WorldTamil-LLaMA Open Tamil language model based on LLaMA 2Regional · Open weights · 2023 BioGPT 🇺🇸 United StatesBioGPT A generative Transformer trained on biomedical writing for text and mining tasksDomain · Open weights · 2022 fnMagistral 🇫🇷 FranceMagistral Mistral AI's first reasoning model, in open and enterprise versionsReasoning · Open weights · 2025 imgMistral Medium 3.5 🇫🇷 FranceMistral Medium 3.5 A 128B multimodal model with a 256k window for chat, reasoning and codingGeneral · Open weights Med-PaLM 🇺🇸 United StatesMed-PaLM A medical-domain language model aligned from Flan-PaLM using instruction prompt tuning.Domain · Research only · 2022 fnDevstral 🇫🇷 FranceDevstral A 24B agentic coding model built by Mistral AI and All Hands AICode · Open weights · 2025

The weekly digest

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