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

imgfnGrok 🇺🇸 United StatesGrok A chatbot and model line from SpaceX Super Intelligence, launched in 2023.General · API only · 2023 imgwavvidGemma 🇺🇸 United StatesGemma Google DeepMind's open family of Gemini-derived language modelsGeneral · Open weights · 2024 imgLlama 🇺🇸 United StatesLlama Meta AI's family of open-weight language models, from 1B to 2T parametersGeneral · Conditional licence · 2023 BLOOM 🇫🇷 FranceBLOOM A 176-billion-parameter multilingual text model built openly by a volunteer research workshop.General · Conditional licence · 2022 O3 🇺🇸 United StatesO3 Reasoning model from OpenAI designed for step-by-step logical tasks.Reasoning · API only · 2025 Vicuna WorldVicuna An open chat model fine-tuned from LLaMA and Llama 2 by LMSYSGeneral · Conditional licence · 2023 imgfnMuse 🇺🇸 United StatesMuse Meta's multimodal LLM family, successor to Llama, with open and closed variantsGeneral · API only · 2026 fnLlama 3.1 405B 🇺🇸 United StatesLlama 3.1 405B Meta's largest openly available language model, released in 2024General · Conditional licence · 2024 imgLlama 3.2 🇺🇸 United StatesLlama 3.2 Small text models and vision models from Meta for edge devices and image tasksMultimodal · Open weights · 2024 Code Llama 🇺🇸 United StatesCode Llama Meta's code-specialised family of Llama 2 models in four sizesCode · Conditional licence · 2023 fnCodestral 🇫🇷 FranceCodestral Mistral AI's 22B open-weight model built for code generation across 80+ languagesCode · Conditional licence PLLuM 🇵🇱 PolandPLLuM Polish-focused large language model familyGeneral · Open weights · 2024 Mistral Saba 🇫🇷 FranceMistral Saba A 24B regional language model for Arabic and South Asian languagesRegional · API only · 2025 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 fnLlama-3.1-Nemotron-Ultra-253B 🇺🇸 United StatesLlama-3.1-Nemotron-Ultra-253B A 253B reasoning model derived from Llama-3.1-405B-InstructReasoning · Conditional licence DeepSeek LLM 67B 🇨🇳 ChinaDeepSeek LLM 67B A 67-billion-parameter open-source model trained on English and Chinese text.General · Conditional licence · 2024 Poro 2 🇫🇮 FinlandPoro 2 Finnish and English instruction-following model based on Llama 3.1General · Conditional licence EXAONE 3.5 🇰🇷 South KoreaEXAONE 3.5 LG AI Research open language model series for real-world tasksGeneral · Conditional licence · 2024 fnEXAONE 4.0 🇰🇷 South KoreaEXAONE 4.0 Unified language model with reasoning and non-reasoning modesGeneral · Conditional licence · 2025 imgwavfnFanar 🇶🇦 QatarFanar Arabic-centric multimodal generative AI platform and modelsMultimodal · API only · 2025 Llama-3-ELYZA-JP-8B 🇯🇵 JapanLlama-3-ELYZA-JP-8B Japanese-tuned Llama 3 model by ELYZAGeneral · Conditional licence Sarvam-1 🇮🇳 IndiaSarvam-1 A 2-billion parameter language model for Indian languages.Regional · Conditional licence · 2024 Krutrim-1 🇮🇳 IndiaKrutrim-1 Multilingual language model for Indian languagesGeneral · Conditional licence · 2024 imgChitrarth 🇮🇳 IndiaChitrarth Multilingual vision-language model for ten Indian languages and English.Multimodal · Conditional licence OPT 🇺🇸 United StatesOPT Meta AI's family of open decoder-only language models from 125M to 175B parametersGeneral · Conditional licence · 2022 fnTyphoon 🇹🇭 ThailandTyphoon Thai-focused large language model series by SCB 10XGeneral · Conditional licence · 2024 Llama 3 🇺🇸 United StatesLlama 3 Meta's open-weight language model family in 8B and 70B sizesGeneral · Conditional licence · 2024 fnMinistral 3B and 8B 🇫🇷 FranceMinistral 3B and 8B Two small Mistral AI models built for on-device and edge computing.Small · API only · 2024 Qwen2 🇨🇳 ChinaQwen2 Open-weight language model series from AlibabaGeneral · Open weights · 2024 Sahabat-AI 🇮🇩 Indonesia and 1 moreSahabat-AI Indonesian language model family by GoTo and IndosatRegional · Conditional licence fnLlama 3.3 70B 🇺🇸 United StatesLlama 3.3 70B A text-only 70B instruction-tuned model from Meta's Llama 3 line.General · Conditional licence Param-1 🇮🇳 IndiaParam-1 Bilingual and multilingual language models from India.General · Conditional licence fnNorth Mini Code 🇺🇸 United StatesNorth Mini Code A 30B sparse mixture-of-experts model for code and terminal agent workCode · Conditional licence imgwavGemini 2.0 Flash 🇺🇸 United StatesGemini 2.0 Flash Google DeepMind's fast multimodal workhorse model for agentic appsGeneral · API only · 2024 Galactica 🇺🇸 United StatesGalactica A language model trained on scientific text for research tasksDomain · Conditional licence · 2022 Orca 2 🇺🇸 United StatesOrca 2 A small LLaMA-2-based model trained on synthetic data to reason.Small · Conditional licence · 2023 imgwavfnGrok 4 🇺🇸 United StatesGrok 4 xAI's flagship reasoning model with native tool use and live searchGeneral · API only · 2025 imgGrok-2 🇺🇸 United StatesGrok-2 xAI's 2024 chat and reasoning model, with a smaller sibling, Grok-2 miniGeneral · Conditional licence · 2024 Gemma 🇺🇸 United StatesGemma Small open-weight language models from Google, in 2B and 7B sizesGeneral · Conditional licence · 2024 imgMedGemma 🇺🇸 United StatesMedGemma Medical vision-language models built on Gemma 3 for images and textMultimodal · Conditional licence · 2025

The weekly digest

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