Ollama v0.32.3 Released July 23, 2026 with GPU Support Expansions and Model Fixes | Tool Update
Ollama released v0.32.3 on July 23, 2026 at 00:44 UTC as a signed release (commit fce745f) by @github actions, addressing model downloads that stall before sen…
Published on MyPrivateClaw
Jul 23, 2026, 11:27 PM UTC
Coverage date
Jul 23, 2026
Last updated
Jul 25, 2026, 6:49 AM UTC
News summary
Ollama released v0.32.3 on July 23, 2026 at 00:44 UTC as a signed release (commit fce745f) by @github actions, addressing model downloads that stall before sending data. Ollama v0.32.3 restored Claude Code Channels and fixed Anthropic thinking streams. Ollama v0.32.3 expanded GPU support with CUDA on Windows ARM64, B200 support through CUDA 12, and lower memory use on Linux CUDA/ROCm iGPUs. Ollama v0.32.3 added chat, thinking, and tool calling support for Laguna 2.1 models, including a Metal inference fix. Ollama v0.32.3 fixed GLM tool calls being silently dropped at the end of generation. Ollama v0.32.3 updated the MLX and llama.cpp engines.