feat(iOS): 更新MNN后端模型配置优化性能

将MNN主模型从Qwen3.5-4B(~2.64GiB)降级为Qwen3.5-2B(~1.1GiB),因为4B版本
实测运行过慢,影响用户体验。iPhone17+/SME2设备使用2B模型,保留MLX
兜底方案用于模拟器和备用场景,确保AI推理性能和存储效率的平衡。
```
This commit is contained in:
link2026
2026-06-09 22:20:07 +08:00
parent ca5a3fa38b
commit b79ae54b7b
40 changed files with 1327 additions and 452 deletions

View File

@@ -96,7 +96,7 @@ struct RootView: View {
DiaryQuickSheet()
}
.sheet(isPresented: $showIndicator) {
// : VL ()
// : VL ()
IndicatorQuickSheet(onRequestCamera: {
showIndicator = false
DispatchQueue.main.asyncAfter(deadline: .now() + 0.3) {