RealFeedApp beta

New models Gemma4, Qwen3.6 and Qwen3.5 added in v0.40.0

Version 0.40.0 automatically uses MLX for execution on Apple Silicon, adding support for Qwen3.8, Gemma4, and Nimble tev1.

Field
tools and releases
What they did
Version 0.40.0 makes MLX the default runtime for models on Apple Silicon devices, adding support for Gemma4, Qwen3.6, Qwen3.5, and decision models like Nimble, Tev1, Clef, and Clef-Flash.
Why it matters
This allows users to automatically leverage Apple Silicon processors for model execution without requiring additional configuration.
#ollama#mlx#apple silicon#llm

Read the original →