News
ResearchOpenAI pens AI safety agreement with four firmsReleasesOVHcloud 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 improvementFrontierOpenAI鈥檚 New Hacking Model Found Dozens Of Holes In Apple TechFrontierMicrosoft unveils AI models for coding, cybersecurity as it takes on Anthropic, OpenAIResearchOpenAI pens AI safety agreement with four firmsReleasesOVHcloud 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 improvementFrontierOpenAI鈥檚 New Hacking Model Found Dozens Of Holes In Apple TechFrontierMicrosoft unveils AI models for coding, cybersecurity as it takes on Anthropic, OpenAI
EveryLLM

Hybrid designs

Jamba and others that mix attention with state-space layers. 31 models on EveryLLM so far.

Hybrid models combine a few attention layers with many cheaper layers of another kind, usually state-space (Mamba) layers or forms of linear attention. Attention gives exact recall over the context, while the cheaper layers carry most of the load, cutting the memory needed for long inputs and speeding up generation. Since 2024 hybrids have moved from experiments into production models from AI21, Nvidia, IBM and Alibaba.

Jamba and after

AI21 Labs in Tel Aviv released Jamba in March 2024, mixing transformer and Mamba layers with a mixture of experts: 52 billion parameters in total, 12 billion active, and a context window of 256,000 tokens. Nvidia's Nemotron Nano 2 (August 2025) has 62 layers, of which only 6 use self-attention, and Nvidia reported up to six times the throughput of a similar-sized transformer on reasoning tasks.

Mainstream releases

IBM's Granite 4.0 family (October 2025) pairs Mamba-2 and transformer layers at roughly nine to one, and IBM reported over 70% less memory for long inputs. Alibaba's Qwen3-Next (September 2025) alternates three Gated DeltaNet layers, a form of linear attention, with one gated attention layer, in an 80-billion-parameter mixture of experts with 3 billion active. Such designs aim at long documents and agents that run for many steps.

Famous hybrid models

Further reading

imgwavvidNemotron 馃嚭馃嚫 United StatesNemotron Nvidia family of language and multimodal models for enterprise and reasoningGeneral 路 Conditional licence 路 2023 fnGranite 4.0 馃嚭馃嚫 United StatesGranite 4.0 IBM's hybrid Mamba/transformer language models for enterprise workGeneral 路 Open weights 路 2025 fnSolar Open 2 馃嚢馃嚪 South KoreaSolar Open 2 250B parameter open-weight model for agentic tasksGeneral 路 Open weights 路 2026 RecurrentGemma 馃嚭馃嚫 United StatesRecurrentGemma Open language models using Google's Griffin recurrent-plus-attention architectureGeneral 路 Open weights 路 2024 MiMo-V2-Flash 馃嚚馃嚦 ChinaMiMo-V2-Flash High-speed MoE language model for reasoning and agentsGeneral 路 Open weights Snowflake Arctic 馃嚭馃嚫 United StatesSnowflake Arctic Open enterprise language model with hybrid MoE designGeneral 路 Open weights 路 2024 fnNemotron Nano 2 馃嚭馃嚫 United StatesNemotron Nano 2 A 9B hybrid Mamba-Transformer model for reasoning and chat, from NVIDIA.General 路 Open weights 路 2025 fnNemotron 3 Super 馃嚭馃嚫 United StatesNemotron 3 Super NVIDIA's 120B hybrid MoE language model with 12B active parameters and 1M-token contextGeneral 路 Conditional licence 路 2026 Zamba WorldZamba A 7-billion parameter hybrid language model combining Mamba and transformer layers.General 路 Open weights 路 2024 fnLFM2 馃嚭馃嚫 United StatesLFM2 Hybrid language models for edge and on-device useSmall 路 Open weights PLaMo 2 馃嚡馃嚨 JapanPLaMo 2 Japanese-focused large language model series by Preferred NetworksGeneral 路 Open weights 路 2025 fnQwen3-Next-80B-A3B 馃嚚馃嚦 ChinaQwen3-Next-80B-A3B An 80-billion parameter hybrid model with ultra-long context support.General 路 Open weights imgfnQwen3.5-397B-A17B 馃嚚馃嚦 ChinaQwen3.5-397B-A17B A large multimodal language model with sparse activation.General 路 Open weights fnEXAONE 4.0 馃嚢馃嚪 South KoreaEXAONE 4.0 Unified language model with reasoning and non-reasoning modesGeneral 路 Conditional licence 路 2025 Falcon-H1R-7B 馃嚘馃嚜 United Arab EmiratesFalcon-H1R-7B A 7-billion parameter reasoning model with hybrid architectureReasoning 路 Open weights 路 2026 Falcon-H1 馃嚘馃嚜 United Arab EmiratesFalcon-H1 Hybrid transformer and state-space model series by TIIGeneral 路 Open weights 路 2025 Kimi Linear 馃嚚馃嚦 ChinaKimi Linear Hybrid linear attention model with 48 billion parametersGeneral 路 Open weights 路 2025 MiniMax-Text-01 馃嚚馃嚦 ChinaMiniMax-Text-01 A large language model with a four million token context window.General 路 Open weights 路 2025 ERNIE 3.0 馃嚚馃嚦 ChinaERNIE 3.0 Knowledge-enhanced pre-training model for language tasksGeneral 路 Research only 路 2021 Hunyuan-TurboS 馃嚚馃嚦 ChinaHunyuan-TurboS Hybrid Mamba-Transformer MoE model by TencentGeneral 路 API only 路 2025 MiMo-V2.5-Pro 馃嚚馃嚦 ChinaMiMo-V2.5-Pro Open-source MoE language model with 1M token contextGeneral 路 Open weights Jamba2 Mini WorldJamba2 Mini A small open-weights SSM-Transformer model for enterprise workSmall 路 Open weights Zamba2 馃嚭馃嚫 United StatesZamba2 Hybrid Mamba2-transformer language model suite by ZyphraGeneral 路 Open weights 路 2024 fnNemotron 3 Nano 馃嚭馃嚫 United StatesNemotron 3 Nano NVIDIA's 30B hybrid Mamba-Transformer MoE model for reasoning and agentsGeneral 路 Conditional licence 路 2025 Jamba 馃嚠馃嚤 IsraelJamba Hybrid open-weights language model with long contextGeneral 路 Open weights 路 2024

The weekly digest

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