InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
Paper
•
2508.18265
•
Published
•
45
InternVL3.5
-
-
OpenGVLab/InternVL3_5-241B-A28B
Image-Text-to-Text • 241B • Updated • 51 -
OpenGVLab/InternVL3_5-38B
Image-Text-to-Text • 38B • Updated • 6 -
OpenGVLab/InternVL3_5-30B-A3B
Image-Text-to-Text • 31B • Updated • 5 -
OpenGVLab/InternVL3_5-GPT-OSS-20B-A4B-Preview
Image-Text-to-Text • 0.4B • Updated • 10 -
OpenGVLab/InternVL3_5-14B
Image-Text-to-Text • 15B • Updated • 6 -
OpenGVLab/InternVL3_5-8B
Image-Text-to-Text • 9B • Updated • 10 -
OpenGVLab/InternVL3_5-4B
Image-Text-to-Text • 5B • Updated • 3 -
OpenGVLab/InternVL3_5-2B
Image-Text-to-Text • 2B • Updated • 3 -
OpenGVLab/InternVL3_5-1B
Image-Text-to-Text • 1B • Updated • 4 -
OpenGVLab/InternVL3_5-241B-A28B-MPO
Image-Text-to-Text • 241B • Updated • 1 -
OpenGVLab/InternVL3_5-38B-MPO
Image-Text-to-Text • 38B • Updated • 1 -
OpenGVLab/InternVL3_5-30B-A3B-MPO
Image-Text-to-Text • 31B • Updated • 2 -
OpenGVLab/InternVL3_5-14B-MPO
Image-Text-to-Text • 15B • Updated • 1 -
OpenGVLab/InternVL3_5-8B-MPO
Image-Text-to-Text • 9B • Updated • 1 -
OpenGVLab/InternVL3_5-4B-MPO
Image-Text-to-Text • 5B • Updated • 2 -
OpenGVLab/InternVL3_5-2B-MPO
Image-Text-to-Text • 2B • Updated • 1 -
OpenGVLab/InternVL3_5-1B-MPO
Image-Text-to-Text • 1B • Updated • 2 -
OpenGVLab/InternVL3_5-241B-A28B-Instruct
Image-Text-to-Text • 241B • Updated • 5 -
OpenGVLab/InternVL3_5-38B-Instruct
Image-Text-to-Text • 38B • Updated • 1 -
OpenGVLab/InternVL3_5-30B-A3B-Instruct
Image-Text-to-Text • 31B • Updated • 5 -
OpenGVLab/InternVL3_5-14B-Instruct
Image-Text-to-Text • 15B • Updated • 2 -
OpenGVLab/InternVL3_5-8B-Instruct
Image-Text-to-Text • 9B • Updated • 2 -
OpenGVLab/InternVL3_5-4B-Instruct
Image-Text-to-Text • 5B • Updated • 1 -
OpenGVLab/InternVL3_5-2B-Instruct
Image-Text-to-Text • 2B • Updated • 1 -
OpenGVLab/InternVL3_5-1B-Instruct
Image-Text-to-Text • 1B • Updated • 1 -
OpenGVLab/InternVL3_5-241B-A28B-Pretrained
Image-Text-to-Text • 241B • Updated • 1 -
OpenGVLab/InternVL3_5-38B-Pretrained
Image-Text-to-Text • 38B • Updated • 1 -
OpenGVLab/InternVL3_5-30B-A3B-Pretrained
Image-Text-to-Text • 31B • Updated • 1 -
OpenGVLab/InternVL3_5-14B-Pretrained
Image-Text-to-Text • 15B • Updated • 1 -
OpenGVLab/InternVL3_5-8B-Pretrained
Image-Text-to-Text • 9B • Updated • 1 -
OpenGVLab/InternVL3_5-4B-Pretrained
Image-Text-to-Text • 5B • Updated • 1 -
OpenGVLab/InternVL3_5-2B-Pretrained
Image-Text-to-Text • 2B • Updated • 1 -
OpenGVLab/InternVL3_5-1B-Pretrained
Image-Text-to-Text • 1B • Updated • 1