Kimi K2.5 Moonshot's most powerful model moonshotai/Kimi-K2.5 Image-Text-to-Text • 1.1T • Updated Feb 27 • 5.35M • • 2.74k Kimi K2.5: Visual Agentic Intelligence Paper • 2602.02276 • Published Feb 2 • 264
Kimi-Linear-A3B Moonshot's experimental MoE model with Kimi Delta Attention moonshotai/Kimi-Linear-48B-A3B-Instruct Text Generation • 49B • Updated Dec 16, 2025 • 60.8k • 556 moonshotai/Kimi-Linear-48B-A3B-Base Text Generation • 49B • Updated Jan 30 • 755 • 72 Kimi Linear: An Expressive, Efficient Attention Architecture Paper • 2510.26692 • Published Oct 30, 2025 • 132
Kimi Linear: An Expressive, Efficient Attention Architecture Paper • 2510.26692 • Published Oct 30, 2025 • 132
Kimi-Audio-7B Kimi audio 7B models moonshotai/Kimi-Audio-7B Text-to-Speech • 10B • Updated May 29, 2025 • 90 • 78 moonshotai/Kimi-Audio-7B-Instruct Text-to-Speech • 10B • Updated May 29, 2025 • 41.6k • 391 moonshotai/Kimi-Audio-GenTest Viewer • Updated Apr 28, 2025 • 191 • 78 • 9
Kimi-K2 Moonshot's MoE LLMs with 1 trillion parameters, exceptional on agentic intellegence moonshotai/Kimi-K2-Thinking Text Generation • 1.1T • Updated Jan 30 • 84.4k • • 1.69k moonshotai/Kimi-K2-Instruct-0905 Text Generation • 1T • Updated Jan 30 • 347k • • 698 moonshotai/Kimi-K2-Instruct Text Generation • 1T • Updated Jan 30 • 227k • • 2.34k moonshotai/Kimi-K2-Base Text Generation • Updated Jan 30 • 8.56k • 298
Kimi-VL-A3B Moonshot's efficient MoE VLMs, exceptional on agent, long-context, and thinking Running on Zero Agents Featured 196 Chat with Kimi-VL-A3B-Thinking-2506 🤔 196 Chat with Kimi-VL: respond to text, images, video, PDFs moonshotai/Kimi-VL-A3B-Thinking-2506 Image-Text-to-Text • 16B • Updated Jan 30 • 43.9k • 355 moonshotai/Kimi-VL-A3B-Instruct Image-Text-to-Text • 16B • Updated Jan 30 • 280k • 258 moonshotai/Kimi-VL-A3B-Thinking Image-Text-to-Text • 16B • Updated Jan 30 • 104k • 447
Running on Zero Agents Featured 196 Chat with Kimi-VL-A3B-Thinking-2506 🤔 196 Chat with Kimi-VL: respond to text, images, video, PDFs
Moonlight-A3B Moonshot's Compute-efficient MoE LLM, first Scaling Up of Muon Optimizer moonshotai/Moonlight-16B-A3B-Instruct Text Generation • 16B • Updated Jan 30 • 77.3k • 194 moonshotai/Moonlight-16B-A3B Text Generation • 16B • Updated Jan 30 • 63.5k • 112 Muon is Scalable for LLM Training Paper • 2502.16982 • Published Feb 24, 2025 • 12
Kimi K2.5 Moonshot's most powerful model moonshotai/Kimi-K2.5 Image-Text-to-Text • 1.1T • Updated Feb 27 • 5.35M • • 2.74k Kimi K2.5: Visual Agentic Intelligence Paper • 2602.02276 • Published Feb 2 • 264
Kimi-K2 Moonshot's MoE LLMs with 1 trillion parameters, exceptional on agentic intellegence moonshotai/Kimi-K2-Thinking Text Generation • 1.1T • Updated Jan 30 • 84.4k • • 1.69k moonshotai/Kimi-K2-Instruct-0905 Text Generation • 1T • Updated Jan 30 • 347k • • 698 moonshotai/Kimi-K2-Instruct Text Generation • 1T • Updated Jan 30 • 227k • • 2.34k moonshotai/Kimi-K2-Base Text Generation • Updated Jan 30 • 8.56k • 298
Kimi-Linear-A3B Moonshot's experimental MoE model with Kimi Delta Attention moonshotai/Kimi-Linear-48B-A3B-Instruct Text Generation • 49B • Updated Dec 16, 2025 • 60.8k • 556 moonshotai/Kimi-Linear-48B-A3B-Base Text Generation • 49B • Updated Jan 30 • 755 • 72 Kimi Linear: An Expressive, Efficient Attention Architecture Paper • 2510.26692 • Published Oct 30, 2025 • 132
Kimi Linear: An Expressive, Efficient Attention Architecture Paper • 2510.26692 • Published Oct 30, 2025 • 132
Kimi-VL-A3B Moonshot's efficient MoE VLMs, exceptional on agent, long-context, and thinking Running on Zero Agents Featured 196 Chat with Kimi-VL-A3B-Thinking-2506 🤔 196 Chat with Kimi-VL: respond to text, images, video, PDFs moonshotai/Kimi-VL-A3B-Thinking-2506 Image-Text-to-Text • 16B • Updated Jan 30 • 43.9k • 355 moonshotai/Kimi-VL-A3B-Instruct Image-Text-to-Text • 16B • Updated Jan 30 • 280k • 258 moonshotai/Kimi-VL-A3B-Thinking Image-Text-to-Text • 16B • Updated Jan 30 • 104k • 447
Running on Zero Agents Featured 196 Chat with Kimi-VL-A3B-Thinking-2506 🤔 196 Chat with Kimi-VL: respond to text, images, video, PDFs
Kimi-Audio-7B Kimi audio 7B models moonshotai/Kimi-Audio-7B Text-to-Speech • 10B • Updated May 29, 2025 • 90 • 78 moonshotai/Kimi-Audio-7B-Instruct Text-to-Speech • 10B • Updated May 29, 2025 • 41.6k • 391 moonshotai/Kimi-Audio-GenTest Viewer • Updated Apr 28, 2025 • 191 • 78 • 9
Moonlight-A3B Moonshot's Compute-efficient MoE LLM, first Scaling Up of Muon Optimizer moonshotai/Moonlight-16B-A3B-Instruct Text Generation • 16B • Updated Jan 30 • 77.3k • 194 moonshotai/Moonlight-16B-A3B Text Generation • 16B • Updated Jan 30 • 63.5k • 112 Muon is Scalable for LLM Training Paper • 2502.16982 • Published Feb 24, 2025 • 12