Kimi-VL
A highly efficient open-source expert-mixed visual language model with multi-modal reasoning capabilities.
ChineseSelectionProductivityMulti-modalReasoning
Kimi-VL is an advanced expert-mixed visual language model designed for multi-modal reasoning, long-context understanding, and powerful agent capabilities. This model excels in several complex domains, boasting efficient 2.8B parameters while exhibiting outstanding mathematical reasoning and image understanding capabilities. Kimi-VL sets a new standard for multi-modal models with its optimized computational performance and ability to handle long inputs.
Kimi-VL Visit Over Time
Monthly Visits
492133528
Bounce Rate
36.20%
Page per Visit
6.1
Visit Duration
00:06:33