v0.32.3

Summary

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 : v0.32.1...v0.32.3

News Radar provides aggregated summaries. Full content and copyright remain with the original publisher.