/
← Accept All   Archive
Ollama BlogTools

Faster Gemma 4 on MLX with multi-token prediction

June 29

Gemma 4 is now significantly faster in Ollama 0.31 on Apple Silicon via multi-token prediction (MTP), powered by MLX. Performance is now up to 90% faster when used with coding agents, as measured using the Aider polyglot

Read at Ollama Blog ↗

More from Ollama Blog on Accept All.