Compact: 1 to 10 billion
Phi, Gemma, Llama 3 8B, Mistral 7B and most on-device and edge models. 82 models.
WorldRWKV-7 Goose
Recurrent language model with constant memory usageGeneral · Open weights · 2025
WorldZamba
A 7-billion parameter hybrid language model combining Mamba and transformer layers.General · Open weights · 2024
WorldEagle and Finch
Efficient recurrent sequence models with matrix statesGeneral · Fully open · 2024
🇺🇸 United StatesZamba2
Hybrid Mamba2-transformer language model suite by ZyphraGeneral · Open weights · 2024
🇦🇪 United Arab EmiratesFalcon Mamba 7B
A 7-billion parameter language model using the Mamba architecture.General · Open weights · 2024