Search: moe
Concepts
🇺🇸 United StatesOLMoE
Open mixture-of-experts language model with 1 billion active parametersGeneral · Fully open · 2024
🇨🇳 ChinaDeepSeekMoE
Mixture-of-experts language model architecture by DeepSeek AIGeneral · Open weights · 2024
🇨🇳 ChinaMiMo-V2-Flash
High-speed MoE language model for reasoning and agentsGeneral · Open weights
🇺🇸 United StatesSnowflake Arctic
Open enterprise language model with hybrid MoE designGeneral · Open weights · 2024
🇺🇸 United StatesNemotron 3 Super
NVIDIA's 120B hybrid MoE language model with 12B active parameters and 1M-token contextGeneral · Conditional licence · 2026
🇮🇳 IndiaParam-2-17B
Multilingual MoE model for Indian languages and reasoningGeneral · Open weights
WorldINTELLECT-3
Open 106B MoE reasoning model from Prime IntellectReasoning · Open weights
🇺🇸 United StatesTrinity Large
398B-parameter sparse MoE model family by Arcee AIGeneral · Open weights · 2026
🇨🇳 ChinaDeepSeek-V4-Pro
1.6T parameter MoE model with one million token contextGeneral · Open weights · 2026
🇨🇳 ChinaDeepSeek-V4.1-Flash
Multimodal MoE model with efficient KV cache compressionMultimodal · Open weights
🇰🇷 South KoreaA.X K1
Sparse MoE model with controllable reasoning depthGeneral · Open weights · 2026
🇨🇳 ChinaMiniCPM
Efficient small language models for end-side devicesGeneral · Open weights · 2024
🇨🇳 ChinaLongCat-2.5
Multimodal MoE model for long-horizon agentic tasksMultimodal · Open weights
🇨🇳 ChinaLongCat-2.0
A 1.6 trillion parameter MoE language model from Meituan.General · Open weights
🇮🇳 IndiaSarvam-30B
Open-weight MoE model for Indian languages and codingGeneral · Open weights
🇨🇳 ChinaLongCat-Flash
Efficient 560B parameter MoE model for agentic tasksGeneral · Open weights · 2025
🇨🇳 ChinaHunyuan-A13B
Open-source MoE language model with 80 billion total parametersGeneral · Open weights · 2025
🇨🇳 ChinaHunyuan-TurboS
Hybrid Mamba-Transformer MoE model by TencentGeneral · API only · 2025
🇨🇳 ChinaMiMo-V2.5-Pro
Open-source MoE language model with 1M token contextGeneral · Open weights
🇨🇳 ChinaStep-3.5-Flash
Open-source MoE model for reasoning and agentsGeneral · Open weights · 2026
🇮🇳 IndiaSarvam-105B
Open-weight MoE model for Indian languages and reasoningGeneral · Open weights
🇨🇳 ChinaHunyuan-Large
Open-source mixture of experts model with 389 billion parametersGeneral · Open weights · 2024
🇮🇳 IndiaParam-1
Bilingual and multilingual language models from India.General · Conditional licence
🇨🇳 ChinaMiniMax-M2
Open-source MoE model for coding and agentsCode · Open weights
🇺🇸 United StatesNemotron 3 Nano
NVIDIA's 30B hybrid Mamba-Transformer MoE model for reasoning and agentsGeneral · Conditional licence · 2025
WorldMM1
A family of multimodal language models up to 30B parameters, dense and MoE.Multimodal · Research only · 2024
WorldStep-5-Preview
Agentic model with 600B parameters and 1M token contextGeneral · Open weights · 2026
🇨🇳 ChinaERNIE 5.5 Flash
Efficient sparse MoE language model with 280B total parametersGeneral · Open weights