mlx @ollama!

Ollama released a preview version (0.19) on March 31, 2026, built on top of Apple's open-source MLX framework, enabling local LLMs to run significantly faster on Apple Silicon Macs by leveraging the unified memory architecture shared by the CPU and GPU. The update delivers 1.6x faster prompt processing and 2x faster response generation , with M5-series chips seeing the largest improvements thanks to Apple's new GPU Neural Accelerators. The preview requires a Mac with more than 32GB of unified memory and currently supports only one model — the 35-billion-parameter Qwen3.5 from Alibaba — with broader model support planned.

There were some exceptionally cool demos from @ollama and omlx using MLX to run Qwen 3.5 and Gemma 4 on Apple silicon. The capabilities of l…
Google's Gemma 4 is pretty wild. You can now run it locally with OpenClaw in 3 steps. 1. Install Ollama 2. Pull Gemma 4 model 3. Launch Open…
MLX creator @awnihannun sharing the story of MLX. Apple management called him right after the launch: “why didn’t you tell us this was going…
Share your Gemma 4 builds or the model variants you’re training in the replies below!
Lots of love for Gemma 4! Team just told me it’s already had 10M+ downloads since last week’s launch. Gemma models have now been downloaded …
We love seeing what you’ve built with Gemma 4, the open model family that we released last week. Here are a few fun examples, described by t…

Source: model-releases

Related