/
← Accept All   週ごとのアーカイブ
Ollama BlogTools

Faster Gemma 4 on MLX with multi-token prediction

6月29日

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

Ollama Blogで読む ↗

Ollama Blogの他の記事