ollama v0.33.1 adds structured output to its MLX runner and fixes Metal GPU timeouts loading models from slow storage

GitHub·medium signalXBlueskyLinkedInCopy link

Released 2026-08-26, v0.33.1 brings MLX support for Qwen3.8 Flash Next, adds structured output support to mlxrunner, and stops Metal GPU timeouts when loading models from slow storage. It also makes external cmake compat patches idempotent and pulls in MLX and llama.cpp updates. Structured output on the MLX path is the practical unlock: it means Apple Silicon local inference can now be driven by JSON-schema-constrained tool calls the same way the llama.cpp path already could.