Model Releases
Gemma 4 is now nearly 90% faster on Apple Silicon with Ollama using MLX! The speedup comes from improved multi-token prediction (MTP), now o…
Gemma 4 is now nearly 90% faster on Apple Silicon with Ollama using MLX! The speedup comes from improved multi-token prediction (MTP), now on by default for Gemma 4, with more models to come. Ollama a
Gemma 4 is now nearly 90% faster on Apple Silicon with Ollama using MLX! The speedup comes from improved multi-token prediction (MTP), now on by default for Gemma 4, with more models to come. Ollama automatically tunes how many tokens to draft as it runs, so it never slows generation down when speculation no longer contributes to a speedup.
Source: Ollama (X) | 2026-07-01