Show HN: Open-source engine running Gemma 4 26B in 2 GB RAM on any M-series Mac

Practical AI: Tools, Models & Frameworksinference

What changed

Gemma 4 26B-A4B inference in about 2 GB of RAM A custom Swift + Metal runtime for any Apple Silicon Mac, even the 8 GB ones. When launched from this checkout, the app stores the model in scratch/gemma4.gturbo. swift run -c release TurboFieldfareCLI \ --model scratch/gemma4.gturbo \ --prompt "The capital of France is" \ --max-new 64 \ --temperature 0This example deliberately requests a short greedy completion.

Why it matters

A concrete addition to Practical AI: Tools, Models & Frameworks: it changes what's available to builders today rather than being general commentary.

How it compares

Related prior coverage to compare against:

  • Running a 28.9M parameter LLM on an $8 microcontroller
  • A $500 RL fine-tune of a 9B open model beat frontier models on catalog review
  • Open-weight AI is having its Kubernetes moment

Sources