Gemma 4 5.1B E2B
on 3× M4 16GB
Use cases
summarization
Summary
User reports Gemma 4 E2B at ~45 tokens/s single-task on three M4 Mac minis with 16GB RAM, each handling around 10 parallel tasks at ~6 tokens/s each.
Setup is local inference on Apple Silicon; no engine, quant, or context length stated.
The user asks whether one Mac Studio or more Mac minis would give better throughput for parallel labeling and categorization.