moonshotai/Kimi-K2.5
Open-source native multimodal agentic MoE model with vision-language understanding, tool calling, and thinking modes
Multimodal agentic MoE model with DeepSeek-V3 backbone and MLA attention
Open-source native multimodal agentic MoE model with vision-language understanding, tool calling, and thinking modes
Multimodal agentic MoE model with DeepSeek-V3 backbone and MLA attention
View on HuggingFace
View on ModelScope