Rapid-MLXProduct update
Rapid-MLX · v0.16.0
Rapid-MLX v0.16.0 bundles the runtime dependencies for vision understanding, image generation and video generation in the base package, though individual models still depend on their weights and capability checks. System One can serve Decider and Clef models on native MLX for structured answers and candidate ranking, and OpenJev's published weights are CC BY-NC 4.0 for non-commercial use only. Bonsai 2 27B, Gemma 4 26B and DeepSeek V4 Flash gain experimental TensorFold acceleration profiles. Operators can block automatic downloads of missing model artifacts through a CLI flag, an environment setting or configuration, which is not the same as a full offline mode.
Saved . A shortened excerpt from GitHub Releases; the original publisher retains authorship.