Large: 70 to 300 billion
Llama 3 70B, GPT-3, Falcon 180B and the larger open releases. 69 models.
WorldDBRX
A 132-billion-parameter mixture-of-experts language model from Databricks.General · Conditional licence · 2024
🇷🇺 RussiaAlice AI
Yandex's family of language, vision and image models behind the Alice assistantGeneral · API only · 2023
🇨🇳 ChinaERNIE 5.5 Flash
Efficient sparse MoE language model with 280B total parametersGeneral · Open weights
🇵🇱 PolandPLLuM
Polish-focused large language model familyGeneral · 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
🇨🇳 ChinaDeepSeek-Coder-V2
Open-source mixture-of-experts model for code and mathCode · Open weights · 2024
WorldINTELLECT-3
Open 106B MoE reasoning model from Prime IntellectReasoning · Open weights
🇨🇳 ChinaDeepSeek-V4-Flash
Efficient mixture-of-experts model with one million token contextGeneral · Open weights · 2026
🇨🇳 ChinaQwen1.5
Open-weight language model series with nine sizes and strong multilingual support.General · Open weights · 2024
🇨🇳 ChinaQwen3-235B-A22B
Mixture-of-experts model with switchable reasoning modesGeneral · Open weights · 2025
🇨🇳 ChinaQwen3-Next-80B-A3B
An 80-billion parameter hybrid model with ultra-long context support.General · Open weights
🇨🇳 ChinaQwen3-VL
Vision-language model with deep visual reasoning and long video context.Multimodal · Open weights
🇰🇷 South KoreaSolar Open 100B
102B parameter Mixture-of-Experts model by UpstageGeneral · Conditional licence · 2026
🇰🇷 South KoreaSolar Open 2
250B parameter open-weight model for agentic tasksGeneral · Open weights · 2026
🇨🇳 ChinaHunyuan-A13B
Open-source MoE language model with 80 billion total parametersGeneral · Open weights · 2025
🇨🇳 ChinaSeed1.5-Thinking
A reasoning model from ByteDance Seed using reinforcement learningReasoning · API only · 2025
🇨🇳 ChinaIntern-S1
Open-source multimodal reasoning model for scienceReasoning · Open weights · 2025
🇨🇳 ChinaStep-3.5-Flash
Open-source MoE model for reasoning and agentsGeneral · Open weights · 2026
🇺🇸 United StatesNemotron 3.5 Super VL
NVIDIA's open-weight vision-language model with 120B parameters and 1M-token contextMultimodal · Conditional licence · 2026
🇨🇳 ChinaQwen2
Open-weight language model series from AlibabaGeneral · Open weights · 2024
🇮🇳 IndiaSarvam-105B
Open-weight MoE model for Indian languages and reasoningGeneral · Open weights
🇨🇳 ChinaMiniMax-M2
Open-source MoE model for coding and agentsCode · Open weights
🇨🇳 ChinaDeepSeek-V2
Efficient mixture-of-experts language model with 236 billion parametersGeneral · Open weights · 2024
🇰🇷 South KoreaK-EXAONE
LG AI Research multilingual Mixture-of-Experts modelGeneral · Open weights
🇫🇷 FranceMixtral 8x22B
Sparse mixture-of-experts open model with 39B active parameters out of 141BGeneral · Open weights
🇫🇷 FranceLeanstral 1.5
An open code agent model built for the Lean 4 proof assistantCode · Open weights
🇺🇸 United StatesGpt-oss-120b
OpenAI's open-weight reasoning model that fits on one 80GB GPUReasoning · Open weights · 2025