LLaDA2.1 Paper • 2602.08676 • Published Feb 9 • 73 Text Generation • 16B • Updated Apr 13 • 12.8k • 125 Text Generation • 103B • Updated Apr 13 • 100k • 92
LingBot-World Image-to-Video • Updated Feb 2 • 336 Image-to-Video • Updated Mar 5 • 19 Image-to-Video • Updated Apr 2 • 16.4k • 17 Image-to-Video • Updated about 1 month ago • 4.47k • 5
LingBot-VLA 4B • Updated Apr 30 • 1.2k • 30 4B • Updated Apr 30 • 110 • 19 4B • Updated Apr 30 • 4.07k • 2 4B • Updated Apr 30 • 41 • 2
Ling 2.5 The newest flagship non-reasoning model series. Text Generation • 1T • Updated Feb 16 • 173 • 115
Ming 2.0 Ming is the multi-modal series of any-to-any models developed by Ant Ling team. Any-to-Any • 104B • Updated Feb 12 • 2.43k • 269 Text-to-Speech • 18B • Updated 14 days ago • 991 • 53 Text-to-Speech • 2B • Updated Feb 25 • 16.5k • 38 Audio-to-Audio • 0.8B • Updated Feb 25 • 14 • 12
Zooming-without-Zooming Paper • 2602.11858 • Published Feb 12 • 63 Image-Text-to-Text • 5B • Updated Mar 4 • 242 • 33 Image-Text-to-Text • 9B • Updated Apr 13 • 432 • 46 Viewer • Updated May 28 • 111k • 1.64k • 16
Ling 2.0 Text Generation • 1000B • Updated Apr 13 • 4.48k • • 543 Text Generation • 103B • Updated Sep 26, 2025 • 1.83k • 216 Text Generation • 16B • Updated Apr 13 • 35.2k • 196 16B • Updated Sep 25, 2025 • 427 • 27
TwinFlow A collection of TwinFlow-accelerated diffusion models Paper • 2512.05150 • Published Dec 3, 2025 • 77 Text-to-Image • Updated Dec 29, 2025 • 6 • 126 Text-to-Image • Updated Dec 29, 2025 • 14 • 212
LLaDA Text Generation • 7B • Updated Oct 28, 2025 • 1.37k • 34 7B • Updated Oct 28, 2025 • 1.14k • 72 7B • Updated Oct 28, 2025 • 66 • 9
GroveMoE GroveMoE is an open-source family of large language models developed by the AGI Center, Ant Research Institute. Paper • 2508.07785 • Published Aug 11, 2025 • 30 Text Generation • 33B • Updated Sep 12, 2025 • 14 • 46 Text Generation • 33B • Updated Sep 12, 2025 • 12 • 4
Ling Text Generation • 17B • Updated Aug 10, 2025 • 22 • 77 Text Generation • 17B • Updated Jul 25, 2025 • 37 • 53 Text Generation • 17B • Updated Apr 13 • 43.6k • 58 Text Generation • 17B • Updated May 14, 2025 • 25 • 34
AReaL-boba-2 AReaL-boba-2 Text Generation • Updated Jun 13, 2025 • 384 • 28 Text Generation • Updated Jun 4, 2025 • 183 • 20 Text Generation • Updated Jun 10, 2025 • 195 • 22 Text Generation • Updated Jun 4, 2025 • 194 • 20
Ling 2.6 Ling-2.6 series is designed for real-world agents that require fast responses, strong execution, and high token efficiency, with several sized SKUs. Text Generation • 1T • Updated 12 days ago • 408 • • 472 Text Generation • 107B • Updated 12 days ago • 9.9k • 498 108B • Updated Apr 28 • 295 • 14 107B • Updated Apr 28 • 149 • 17
Sing-Guard Image-Text-to-Text • 2B • Updated 6 days ago • 65 • 6 4B • Updated 6 days ago • 63 • 3 9B • Updated 6 days ago • 67 • 4 2B • Updated 6 days ago • 300 • 3
LingBot-VA Robotics • Updated Apr 24 • 25 Robotics • Updated Apr 24 • 2 Robotics • Updated Apr 24 • 9
LingBot-Depth Depth Estimation • Updated Jan 28 • 72 Depth Estimation • Updated Jan 28 • 9 Updated Apr 17 • 2.41k • 32
DR-Venus 4B • Updated Apr 28 • 43 • 7 4B • Updated Apr 28 • 107 • 13 Paper • 2604.19859 • Published Apr 21 • 54 4B • Updated Apr 28 • 91 • 11
AReaL-SEA Text Generation • 235B • Updated Mar 2 • 18 • 6 33B • Updated Mar 5 • 1.29k • 1 31B • Updated Mar 4 • 762 • 1 31B • Updated Mar 4 • 2.32k • 1
Ring 2.0 Text Generation • 1000B • Updated Oct 28, 2025 • 84 • • 233 Text Generation • 1000B • Updated Oct 28, 2025 • 201 • 20 Text Generation • 1000B • Updated Oct 22, 2025 • 31 • 268 Text Generation • 1000B • Updated Oct 7, 2025 • 7 • 4
LLaDA2.0 Paper • 2604.20796 • Published Apr 22 • 244 Any-to-Any • 16B • Updated May 27 • 7.52k • 247 Any-to-Any • 16B • Updated May 27 • 4.88k • 6 Paper • 2512.15745 • Published Dec 10, 2025 • 90
Ring Ring is a reasoning MoE LLM provided and open-sourced by InclusionAI, derived from Ling. Text Generation • 17B • Updated Aug 18, 2025 • 24 • 50 17B • Updated Aug 5, 2025 • 10 • 61 17B • Updated Aug 6, 2025 • 9 • 36 Text Generation • 17B • Updated Sep 17, 2025 • 14 • 47
AWorld The Agent Runtime for Self-Improvement Text Generation • 33B • Updated Sep 1, 2025 • 10 • 16 8B • Updated Oct 13, 2025 • 8 • 10
UI-Venus Paper • 2602.09082 • Published Feb 9 • 158 Image-Text-to-Text • 31B • Updated Feb 11 • 1.65k • 31 Image-Text-to-Text • 9B • Updated Feb 11 • 6.36k • 28 Image-Text-to-Text • 2B • Updated Feb 11 • 1.1k • 39
ASearcher Updated Aug 13, 2025 • 47 • 30 Updated Aug 13, 2025 • 12 • 24 Updated Aug 13, 2025 • 10 • 23 Updated Aug 13, 2025 • 8 • 24
AReaL-boba Preview • Updated Mar 29, 2025 • 61 • 26 Updated Mar 30, 2025 • 8 • 22 Updated Mar 30, 2025 • 10 • 25
Ming Paper • 2506.09344 • Published Jun 11, 2025 • 33 Any-to-Any • 19B • Updated Oct 27, 2025 • 30 • 200 Any-to-Any • 19B • Updated Aug 29, 2025 • 213 • 86 Any-to-Any • 18B • Updated Nov 24, 2025 • 64 • 80
Ling 2.6 Ling-2.6 series is designed for real-world agents that require fast responses, strong execution, and high token efficiency, with several sized SKUs. Text Generation • 1T • Updated 12 days ago • 408 • • 472 Text Generation • 107B • Updated 12 days ago • 9.9k • 498 108B • Updated Apr 28 • 295 • 14 107B • Updated Apr 28 • 149 • 17
LLaDA2.1 Paper • 2602.08676 • Published Feb 9 • 73 Text Generation • 16B • Updated Apr 13 • 12.8k • 125 Text Generation • 103B • Updated Apr 13 • 100k • 92
Sing-Guard Image-Text-to-Text • 2B • Updated 6 days ago • 65 • 6 4B • Updated 6 days ago • 63 • 3 9B • Updated 6 days ago • 67 • 4 2B • Updated 6 days ago • 300 • 3
LingBot-VA Robotics • Updated Apr 24 • 25 Robotics • Updated Apr 24 • 2 Robotics • Updated Apr 24 • 9
LingBot-World Image-to-Video • Updated Feb 2 • 336 Image-to-Video • Updated Mar 5 • 19 Image-to-Video • Updated Apr 2 • 16.4k • 17 Image-to-Video • Updated about 1 month ago • 4.47k • 5
LingBot-Depth Depth Estimation • Updated Jan 28 • 72 Depth Estimation • Updated Jan 28 • 9 Updated Apr 17 • 2.41k • 32
LingBot-VLA 4B • Updated Apr 30 • 1.2k • 30 4B • Updated Apr 30 • 110 • 19 4B • Updated Apr 30 • 4.07k • 2 4B • Updated Apr 30 • 41 • 2
DR-Venus 4B • Updated Apr 28 • 43 • 7 4B • Updated Apr 28 • 107 • 13 Paper • 2604.19859 • Published Apr 21 • 54 4B • Updated Apr 28 • 91 • 11
Ling 2.5 The newest flagship non-reasoning model series. Text Generation • 1T • Updated Feb 16 • 173 • 115
Ming 2.0 Ming is the multi-modal series of any-to-any models developed by Ant Ling team. Any-to-Any • 104B • Updated Feb 12 • 2.43k • 269 Text-to-Speech • 18B • Updated 14 days ago • 991 • 53 Text-to-Speech • 2B • Updated Feb 25 • 16.5k • 38 Audio-to-Audio • 0.8B • Updated Feb 25 • 14 • 12
AReaL-SEA Text Generation • 235B • Updated Mar 2 • 18 • 6 33B • Updated Mar 5 • 1.29k • 1 31B • Updated Mar 4 • 762 • 1 31B • Updated Mar 4 • 2.32k • 1
Zooming-without-Zooming Paper • 2602.11858 • Published Feb 12 • 63 Image-Text-to-Text • 5B • Updated Mar 4 • 242 • 33 Image-Text-to-Text • 9B • Updated Apr 13 • 432 • 46 Viewer • Updated May 28 • 111k • 1.64k • 16
Ring 2.0 Text Generation • 1000B • Updated Oct 28, 2025 • 84 • • 233 Text Generation • 1000B • Updated Oct 28, 2025 • 201 • 20 Text Generation • 1000B • Updated Oct 22, 2025 • 31 • 268 Text Generation • 1000B • Updated Oct 7, 2025 • 7 • 4
Ling 2.0 Text Generation • 1000B • Updated Apr 13 • 4.48k • • 543 Text Generation • 103B • Updated Sep 26, 2025 • 1.83k • 216 Text Generation • 16B • Updated Apr 13 • 35.2k • 196 16B • Updated Sep 25, 2025 • 427 • 27
LLaDA2.0 Paper • 2604.20796 • Published Apr 22 • 244 Any-to-Any • 16B • Updated May 27 • 7.52k • 247 Any-to-Any • 16B • Updated May 27 • 4.88k • 6 Paper • 2512.15745 • Published Dec 10, 2025 • 90
TwinFlow A collection of TwinFlow-accelerated diffusion models Paper • 2512.05150 • Published Dec 3, 2025 • 77 Text-to-Image • Updated Dec 29, 2025 • 6 • 126 Text-to-Image • Updated Dec 29, 2025 • 14 • 212
Ring Ring is a reasoning MoE LLM provided and open-sourced by InclusionAI, derived from Ling. Text Generation • 17B • Updated Aug 18, 2025 • 24 • 50 17B • Updated Aug 5, 2025 • 10 • 61 17B • Updated Aug 6, 2025 • 9 • 36 Text Generation • 17B • Updated Sep 17, 2025 • 14 • 47
LLaDA Text Generation • 7B • Updated Oct 28, 2025 • 1.37k • 34 7B • Updated Oct 28, 2025 • 1.14k • 72 7B • Updated Oct 28, 2025 • 66 • 9
AWorld The Agent Runtime for Self-Improvement Text Generation • 33B • Updated Sep 1, 2025 • 10 • 16 8B • Updated Oct 13, 2025 • 8 • 10
GroveMoE GroveMoE is an open-source family of large language models developed by the AGI Center, Ant Research Institute. Paper • 2508.07785 • Published Aug 11, 2025 • 30 Text Generation • 33B • Updated Sep 12, 2025 • 14 • 46 Text Generation • 33B • Updated Sep 12, 2025 • 12 • 4
UI-Venus Paper • 2602.09082 • Published Feb 9 • 158 Image-Text-to-Text • 31B • Updated Feb 11 • 1.65k • 31 Image-Text-to-Text • 9B • Updated Feb 11 • 6.36k • 28 Image-Text-to-Text • 2B • Updated Feb 11 • 1.1k • 39
Ling Text Generation • 17B • Updated Aug 10, 2025 • 22 • 77 Text Generation • 17B • Updated Jul 25, 2025 • 37 • 53 Text Generation • 17B • Updated Apr 13 • 43.6k • 58 Text Generation • 17B • Updated May 14, 2025 • 25 • 34
ASearcher Updated Aug 13, 2025 • 47 • 30 Updated Aug 13, 2025 • 12 • 24 Updated Aug 13, 2025 • 10 • 23 Updated Aug 13, 2025 • 8 • 24
AReaL-boba-2 AReaL-boba-2 Text Generation • Updated Jun 13, 2025 • 384 • 28 Text Generation • Updated Jun 4, 2025 • 183 • 20 Text Generation • Updated Jun 10, 2025 • 195 • 22 Text Generation • Updated Jun 4, 2025 • 194 • 20
AReaL-boba Preview • Updated Mar 29, 2025 • 61 • 26 Updated Mar 30, 2025 • 8 • 22 Updated Mar 30, 2025 • 10 • 25
Ming Paper • 2506.09344 • Published Jun 11, 2025 • 33 Any-to-Any • 19B • Updated Oct 27, 2025 • 30 • 200 Any-to-Any • 19B • Updated Aug 29, 2025 • 213 • 86 Any-to-Any • 18B • Updated Nov 24, 2025 • 64 • 80