Ollama v0.19

Developer Tools

Massive local model speedup on Apple Silicon with MLX

About

Ollama v0.19 reconstructs Apple Silicon inference using MLX, delivering significantly faster local performance for coding and agent tasks. This update also introduces NVFP4 support along with more intelligent cache reuse, snapshots, and eviction for more responsive sessions.

Launched

April 2, 2026Week 4

Builder

Reviews

Be the first to review

Ollama v0.19

About

Comments