Starstruk Logo MarkStarstruk

v0.32.3

wxt-dev/wxtv0.32.3Jul 23, 2026by github-actions[bot]

AI Summary

A comprehensive update improving integrations, expanding GPU support (CUDA on Windows ARM64, B200), and fixing model download stalls and tool calling issues.

Key Highlights

  • Expanded GPU support including CUDA on Windows ARM64 and B200 support
  • Fixed model downloads that stall before sending data
  • Fixed GLM tool calls being silently dropped
  • Added chat and thinking support for Laguna 2.1 models

Full Release Notes

## What's Changed

- Fixed model downloads that stall before sending data.
- Improved integrations: restored Claude Code Channels, fixed Anthropic thinking streams, and made Hermes Desktop respect `--force-build`.
- Expanded GPU support with CUDA on Windows ARM64, B200 support through CUDA 12, and lower memory use on Linux CUDA/ROCm iGPUs.
- Added chat, thinking, and tool calling support for Laguna 2.1 models, including a Metal inference fix.
- Fixed GLM tool calls being silently dropped at the end of generation.
- Updated the MLX and llama.cpp engines.

**Full Changelog**: https://github.com/ollama/ollama/compare/v0.32.1...v0.32.3