Ollama v0.31.1 Boosts Gemma 4 Performance on Apple Silicon

Core summary

One sentence to understand this update

Ollama's v0.31.1 release significantly accelerates Gemma 4 performance on Apple Silicon, achieving nearly 90% faster token generation on average by utilizing multi-token prediction.

Impact & opportunity

What this could mean

Apple Silicon developers can now achieve much faster local inference with Gemma 4, offering a significant advantage for developing and testing local AI applications.