OpenBMB· @OpenBMB · X·· 3 小时前AI 评分31
AI 导读
本地 VLM 的有趣结果。MiniCPM-V 4.7 35B-A3B 不仅用了更少的 token，还生成了比 Qwen 3.6 35B-A3 更好的体素宝塔。效率 + 质量正在成为多模态模型真正的战场。🔥
正文
Interesting result for local VLMs. MiniCPM-V 4.7 35B-A3B not only used fewer tokens, but also produced a better voxel pagoda than Qwen 3.6 35B-A3. Efficiency + quality is becoming the real battleground for multimodal models.🔥
MiniCPM-V 4.7 beat Qwen 3.6 35B-3A at Pagoda 🏯 @OpenBMB's new 35B-A3 model made a better 3D Voxel Japanese Pagoda while consuming 10% less tokens than Qwen 3.6 35B-3A Run AI models locally -> https://atomic.chat在 X 查看被引用的帖子
来源：OpenBMB · x.com