Ollama v0.31.2 made Gemma 4 ~90% faster on Apple Silicon, for free.

Ollama uses MLX / Shared entities / Shared topic / Earlier coverage

Gemma 4 QAT checkpoints drop the smallest model from 11.4GB to 1.1GB

Linked by a graph relationship (Ollama uses MLX); both cover Gemma, Ollama; overlapping topics (gemma, model, ollama).

Ollama uses MLX / Shared entity: Ollama / Same source domain / Shared topic / Earlier coverage

Timber — Ollama for Classical ML (476 stars, 188 HN points)

Linked by a graph relationship (Ollama uses MLX); both cover Ollama; reported by the same outlet (github.com).

Ollama uses MLX / Shared entities / Shared topic / Earlier coverage

A guide to running a fully local coding agent on a Mac was the day's top AI story on HN.

Linked by a graph relationship (Ollama uses MLX); both cover Apple Silicon, Ollama; overlapping topics (apple, model).

Google shipped a 12B multimodal model that runs on my laptop and hears audio with no encoder

Linked by a graph relationship (Ollama uses MLX); both cover Gemma, MLX; overlapping topics (gemma, model).

Gemma 4 Drops Four Open Models, and the 31B Dense Beats a 397B MoE

Linked by a graph relationship (Ollama uses MLX); both cover Gemma, Ollama; overlapping topics (gemma, model).