Post
iury souza
iurysouza.dev
did:plc:vbo357svte425ow2e4gslurs
Jumped from 20 TPS to 80 TPS ⚡ on my M4 Pro.
The trick is that this version uses a MoE architecture with 3 billion active parameters. That makes it way faster.
I was running the base model via GGUF (ollama), and now running on MLX (vlm - because this is a vision model too).
2026-03-02T13:15:24.457Z