Very large: 300 billion to 1 trillion
PaLM, Llama 3.1 405B, DeepSeek-V3 and the big mixture-of-experts models. 37 models.
🇺🇸 United StatesNemotron
Nvidia family of language and multimodal models for enterprise and reasoningGeneral · Conditional licence · 2023
🇨🇳 ChinaQwen3.5-397B-A17B
A large multimodal language model with sparse activation.General · Open weights
🇨🇳 ChinaHunyuan-TurboS
Hybrid Mamba-Transformer MoE model by TencentGeneral · API only · 2025