Ollama v0.31.1 Accelerates Gemma 4 on Apple Silicon

Core summary

One sentence to understand this update

Ollama's v0.31.1 release significantly boosts Gemma 4 performance on Apple Silicon, achieving nearly 90% faster token generation for coding agents through multi-token prediction (MTP).

Impact & opportunity

What this could mean

Developers using Ollama on Apple Silicon can now leverage Gemma 4 for faster, more efficient local coding agent applications, opening doors for more complex on-device AI.