Kimi K2.5 Moonshot's most powerful model moonshotai/Kimi-K2.7-Code Image-Text-to-Text • 1.1T • Updated Jun 15 • 730k • • 1.29k moonshotai/Kimi-K2.6 Image-Text-to-Text • 1.1T • Updated May 19 • 946k • • 1.57k moonshotai/Kimi-K2.5 Image-Text-to-Text • 1.1T • Updated Apr 30 • 997k • • 2.86k Kimi K2.5: Visual Agentic Intelligence Paper • 2602.02276 • Published Feb 2 • 278
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 • 67.5k • • 567 moonshotai/Kimi-Linear-48B-A3B-Base Text Generation • 49B • Updated Jan 30 • 1.11k • 80 Kimi Linear: An Expressive, Efficient Attention Architecture Paper • 2510.26692 • Published Oct 30, 2025 • 135
Kimi Linear: An Expressive, Efficient Attention Architecture Paper • 2510.26692 • Published Oct 30, 2025 • 135
Kimi-Audio-7B Kimi audio 7B models moonshotai/Kimi-Audio-7B Text-to-Speech • 10B • Updated May 29, 2025 • 136 • 90 moonshotai/Kimi-Audio-7B-Instruct Text-to-Speech • 10B • Updated May 29, 2025 • 90.8k • 411 moonshotai/Kimi-Audio-GenTest Viewer • Updated Apr 28, 2025 • 191 • 64 • 10
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 • 75.7k • • 1.71k moonshotai/Kimi-K2-Instruct-0905 Text Generation • 1T • Updated Jan 30 • 160k • • 785 moonshotai/Kimi-K2-Instruct Text Generation • 1T • Updated Apr 23 • 192k • • 2.37k moonshotai/Kimi-K2-Base Text Generation • 1T • Updated Jan 30 • 8.46k • 304
Kimi-VL-A3B Moonshot's efficient MoE VLMs, exceptional on agent, long-context, and thinking Running on Zero Agents Featured 202 Chat with Kimi-VL-A3B-Thinking-2506 🤔 202 Chat with images, videos, PDFs and get thoughtful responses moonshotai/Kimi-VL-A3B-Thinking-2506 Image-Text-to-Text • 16B • Updated Jan 30 • 7.25k • 371 moonshotai/Kimi-VL-A3B-Instruct Image-Text-to-Text • 16B • Updated Jan 30 • 380k • 275 moonshotai/Kimi-VL-A3B-Thinking Image-Text-to-Text • 16B • Updated Jan 30 • 162k • 449
Running on Zero Agents Featured 202 Chat with Kimi-VL-A3B-Thinking-2506 🤔 202 Chat with images, videos, PDFs and get thoughtful responses
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 • 40.5k • 200 moonshotai/Moonlight-16B-A3B Text Generation • 16B • Updated Jan 30 • 10.9k • 115 Muon is Scalable for LLM Training Paper • 2502.16982 • Published Feb 24, 2025 • 13
Kimi K2.5 Moonshot's most powerful model moonshotai/Kimi-K2.7-Code Image-Text-to-Text • 1.1T • Updated Jun 15 • 730k • • 1.29k moonshotai/Kimi-K2.6 Image-Text-to-Text • 1.1T • Updated May 19 • 946k • • 1.57k moonshotai/Kimi-K2.5 Image-Text-to-Text • 1.1T • Updated Apr 30 • 997k • • 2.86k Kimi K2.5: Visual Agentic Intelligence Paper • 2602.02276 • Published Feb 2 • 278
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 • 75.7k • • 1.71k moonshotai/Kimi-K2-Instruct-0905 Text Generation • 1T • Updated Jan 30 • 160k • • 785 moonshotai/Kimi-K2-Instruct Text Generation • 1T • Updated Apr 23 • 192k • • 2.37k moonshotai/Kimi-K2-Base Text Generation • 1T • Updated Jan 30 • 8.46k • 304
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 • 67.5k • • 567 moonshotai/Kimi-Linear-48B-A3B-Base Text Generation • 49B • Updated Jan 30 • 1.11k • 80 Kimi Linear: An Expressive, Efficient Attention Architecture Paper • 2510.26692 • Published Oct 30, 2025 • 135
Kimi Linear: An Expressive, Efficient Attention Architecture Paper • 2510.26692 • Published Oct 30, 2025 • 135
Kimi-VL-A3B Moonshot's efficient MoE VLMs, exceptional on agent, long-context, and thinking Running on Zero Agents Featured 202 Chat with Kimi-VL-A3B-Thinking-2506 🤔 202 Chat with images, videos, PDFs and get thoughtful responses moonshotai/Kimi-VL-A3B-Thinking-2506 Image-Text-to-Text • 16B • Updated Jan 30 • 7.25k • 371 moonshotai/Kimi-VL-A3B-Instruct Image-Text-to-Text • 16B • Updated Jan 30 • 380k • 275 moonshotai/Kimi-VL-A3B-Thinking Image-Text-to-Text • 16B • Updated Jan 30 • 162k • 449
Running on Zero Agents Featured 202 Chat with Kimi-VL-A3B-Thinking-2506 🤔 202 Chat with images, videos, PDFs and get thoughtful responses
Kimi-Audio-7B Kimi audio 7B models moonshotai/Kimi-Audio-7B Text-to-Speech • 10B • Updated May 29, 2025 • 136 • 90 moonshotai/Kimi-Audio-7B-Instruct Text-to-Speech • 10B • Updated May 29, 2025 • 90.8k • 411 moonshotai/Kimi-Audio-GenTest Viewer • Updated Apr 28, 2025 • 191 • 64 • 10
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 • 40.5k • 200 moonshotai/Moonlight-16B-A3B Text Generation • 16B • Updated Jan 30 • 10.9k • 115 Muon is Scalable for LLM Training Paper • 2502.16982 • Published Feb 24, 2025 • 13