Search: Attention
Concepts
AttentionSelf-attentionMulti-head attentionGrouped-query attentionMulti-head latent attentionFlashAttentionSliding-window attention
Events
🇨🇳 ChinaDeepSeek
A Chinese series of large language models and a free chatbot appGeneral · API only · 2025
🇺🇸 United StatesGPT-5.2
OpenAI's December 2025 GPT release, offered in three modes plus a coding variant.General · API only · 2025
WorldMiniMax-M3
Native multimodal model with 1M context and sparse attentionMultimodal · Open weights
🇨🇳 ChinaMiMo-V2-Flash
High-speed MoE language model for reasoning and agentsGeneral · Open weights
🇺🇸 United StatesDeBERTa
A BERT-style encoder with disentangled attention and an enhanced mask decoder.Encoder · Open weights · 2020
🇨🇳 ChinaDeepSeek-VL2
Mixture-of-experts vision-language model series for multimodal tasksMultimodal · Open weights · 2024
🇨🇳 ChinaDeepSeek-V3.2
Efficient reasoning and agentic AI model with sparse attentionReasoning · Open weights · 2025
🇨🇳 ChinaKimi K3.1 Pro
Open-weight multimodal agentic model with 1M token contextMultimodal · Open weights
🇨🇳 ChinaKimi Linear
Hybrid linear attention model with 48 billion parametersGeneral · Open weights · 2025
🇨🇳 ChinaLongCat-2.0
A 1.6 trillion parameter MoE language model from Meituan.General · Open weights
🇨🇳 ChinaMiniMax-M1
Open-weight reasoning model with hybrid attention and long contextReasoning · Open weights · 2025
🇨🇳 ChinaMiMo-V2.5-Pro
Open-source MoE language model with 1M token contextGeneral · Open weights
🇮🇳 IndiaPragna-1B
Small decoder model for Hindi, Bangla, Gujarati and EnglishSmall · Open weights
WorldJamba2 Mini
A small open-weights SSM-Transformer model for enterprise workSmall · Open weights
🇺🇸 United StatesGranite 4.0
IBM's hybrid Mamba/transformer language models for enterprise workGeneral · Open weights · 2025
🇺🇸 United StatesNemotron 3 Nano
NVIDIA's 30B hybrid Mamba-Transformer MoE model for reasoning and agentsGeneral · Conditional licence · 2025
🇺🇸 United StatesRecurrentGemma
Open language models using Google's Griffin recurrent-plus-attention architectureGeneral · Open weights · 2024