# 0.12.1

## Release Information

- OS support: Tested with Windows-x86 (10), Windows-arm64 (10), Mac-arm64 (14), Linux-x86 (Ubuntu 22.04, Ubuntu 24.04), Linux-arm64 (Ubuntu 24.04)
- QAIRT SDK: Tested with versions (2.49.0, 2.50.0)
- Model Visualization format support: ONNX, TensorFlow, PyTorch (1.x, 2.x), TFLite, Executorch Program, DLC, EAIX, HTP, and QNN JSON

## Highlights

- Weight Free Mode

    - Added an opt-in setting (Settings → Graph → Weight Free Mode) that loads DLC graphs without materializing weight tensor bytes, minimizing memory usage after opening very large DLCs
    - Weight, bias, and other tensors will not display their values when this setting is enabled
    - An inline notification will appear in the tensor inputs section of the node properties view identifying graphs that were loaded in weight-free mode

## Bug Fixes

- Fixed DLC parsing failure for models containing individual weights larger than 2 GB (resolves the known issue called out in 0.12.0)
- Fixed background parser and worker processes not being terminated when the app crashed, which previously left them running until manually killed
- Fixed the flash animation not playing when a node was located from the side panel
- Fixed missing error handlers when the application failed to load models

## Known Issues

- Diffing larger models in the QAIRT Visualizer Graph Panel (i.e., with 40K nodes or more or larger than 1.5 GB) may result in performance degradation or may fail to load altogether due to memory constraints. Upcoming releases will address these limitations to allow extra-large models to be loaded.

## Notices

- QAIRT Visualizer content may include China design and development contributions

Last Published: Sep 14, 2026

[Previous Topic
Notices](https://docs.qualcomm.com/bundle/publicresource/80-87189-1/topics/0_12_0.md)