🤔👀🎬🖥️📖 Kimi-VL-A3B-Thinking-2506: A Quick Navigation
• 79
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
PerceptionBench: Evaluating Atomic Visual Perception in Multimodal Large Language Models
Kimi K3: Open Frontier Intelligence
Articles
Team members 19 private
Open Frontier Intelligence
Moonshot's MoE LLMs with 1 trillion parameters, exceptional on agentic intellegence
-
moonshotai/Kimi-K2-Thinking
Text Generation • 1.1T • Updated • 56.9k • • 1.71k -
moonshotai/Kimi-K2-Instruct-0905
Text Generation • 1T • Updated • 67.5k • • 787 -
moonshotai/Kimi-K2-Instruct
Text Generation • 1T • Updated • 182k • • 2.37k -
moonshotai/Kimi-K2-Base
Text Generation • 1T • Updated • 8.01k • 306
Moonshot's efficient MoE VLMs, exceptional on agent, long-context, and thinking
-
moonshotai/Kimi-VL-A3B-Thinking-2506
Image-Text-to-Text • 16B • Updated • 9.02k • 373 -
moonshotai/Kimi-VL-A3B-Instruct
Image-Text-to-Text • 16B • Updated • 408k • 277 -
moonshotai/Kimi-VL-A3B-Thinking
Image-Text-to-Text • 16B • Updated • 183k • 450 -
moonshotai/MoonViT-SO-400M
Image Feature Extraction • 0.4B • Updated • 3.51k • 91
Moonshot's Compute-efficient MoE LLM, first Scaling Up of Muon Optimizer
Moonshot's large visual-language model
-
moonshotai/Kimi-K2.7-Code
Image-Text-to-Text • 1.1T • Updated • 695k • • 1.35k -
moonshotai/Kimi-K2.6
Image-Text-to-Text • 1.1T • Updated • 877k • • 1.59k -
moonshotai/Kimi-K2.5
Image-Text-to-Text • 1.1T • Updated • 966k • • 2.86k -
Kimi K2.5: Visual Agentic Intelligence
Paper • 2602.02276 • Published • 280
Moonshot's experimental MoE model with Kimi Delta Attention
Kimi audio 7B models
Open Frontier Intelligence
Moonshot's large visual-language model
-
moonshotai/Kimi-K2.7-Code
Image-Text-to-Text • 1.1T • Updated • 695k • • 1.35k -
moonshotai/Kimi-K2.6
Image-Text-to-Text • 1.1T • Updated • 877k • • 1.59k -
moonshotai/Kimi-K2.5
Image-Text-to-Text • 1.1T • Updated • 966k • • 2.86k -
Kimi K2.5: Visual Agentic Intelligence
Paper • 2602.02276 • Published • 280
Moonshot's MoE LLMs with 1 trillion parameters, exceptional on agentic intellegence
-
moonshotai/Kimi-K2-Thinking
Text Generation • 1.1T • Updated • 56.9k • • 1.71k -
moonshotai/Kimi-K2-Instruct-0905
Text Generation • 1T • Updated • 67.5k • • 787 -
moonshotai/Kimi-K2-Instruct
Text Generation • 1T • Updated • 182k • • 2.37k -
moonshotai/Kimi-K2-Base
Text Generation • 1T • Updated • 8.01k • 306
Moonshot's experimental MoE model with Kimi Delta Attention
Moonshot's efficient MoE VLMs, exceptional on agent, long-context, and thinking
-
moonshotai/Kimi-VL-A3B-Thinking-2506
Image-Text-to-Text • 16B • Updated • 9.02k • 373 -
moonshotai/Kimi-VL-A3B-Instruct
Image-Text-to-Text • 16B • Updated • 408k • 277 -
moonshotai/Kimi-VL-A3B-Thinking
Image-Text-to-Text • 16B • Updated • 183k • 450 -
moonshotai/MoonViT-SO-400M
Image Feature Extraction • 0.4B • Updated • 3.51k • 91
Kimi audio 7B models
Moonshot's Compute-efficient MoE LLM, first Scaling Up of Muon Optimizer