Massive local model speedup on Apple Silicon with MLX
Ollama v0.19 rebuilds Apple Silicon inference on top of MLX, bringing much faster local performance for coding and agent workflows. It also adds NVFP4 support and smarter cache reuse, snapshots, and eviction for more responsive sessions.
No comments yet. Be the first!
Real conversations about Ollama v0.19 on X
Post on X
