GPT4V-level open-source multi-modal model based on Llama3-8B
Like zai-org/CogVLM2, 0 likes 0 Bookmark zai-org/CogVLM2, 0 bookmarks 0 Qwen3.8-Flash-Next is the foundation model developed by Qwen Team, Alibaba Group.
Like QwenLM/Qwen3.8-Flash-Next, 0 likes 0 Bookmark QwenLM/Qwen3.8-Flash-Next, 0 bookmarks 0 [CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型
Like OpenGVLab/InternVL, 0 likes 0 Bookmark OpenGVLab/InternVL, 0 bookmarks 0 DeepSeek-VL: Towards Real-World Vision-Language Understanding
Like deepseek-ai/DeepSeek-VL, 0 likes 0 Bookmark deepseek-ai/DeepSeek-VL, 0 bookmarks 0 enseNova-U1: Unifying Multimodal Understanding and Generation with NEO-Unify Architecture
Like smthemex/ComfyUI_SenseNova_U1, 0 likes 0 Bookmark smthemex/ComfyUI_SenseNova_U1, 0 bookmarks 0 A powerful, open-source large language model, including the training data.
Like Azure99/BlossomLM, 0 likes 0 Bookmark Azure99/BlossomLM, 0 bookmarks 0 Open Frontier Intelligence
Like MoonshotAI/Kimi-K3, 0 likes 0 Bookmark MoonshotAI/Kimi-K3, 0 bookmarks 0 [ICML 2026 & EMNLP 2026] Multimodal deep-research MLLM and benchmark. The first long-horizon multimodal deep-research MLLM, extending the number of reasoning turns to dozens and the number of search-engine interactions to hundreds.
Like Osilly/Vision-DeepResearch, 0 likes 0 Bookmark Osilly/Vision-DeepResearch, 0 bookmarks 0 GLM-4.6V/4.5V/4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
Like zai-org/GLM-V, 0 likes 0 Bookmark zai-org/GLM-V, 0 bookmarks 0 
