Benchmark result
gemma-4-e2b-it-mlx on Apple M5 Pro — 93.5 tok/s
Measured with LM Studio on August 26, 2026.
What the model built
Open full screen →The coding scenario asks for a playable game in a single HTML file. This is exactly what the model returned, unedited.
Reproduce this run
toolLM Studio
modelgemma-4-e2b-it-mlx
context32,768
clientv0.4.44+97
Set those in LM Studio, then:
llm-benchmark benchmark --model "gemma-4-e2b-it-mlx" --tool "LM Studio"The client prompts for context length and thinking mode, and for the KV cache dtype on Unsloth Studio. Sampling is left at the model default — the values above are what the tool reported using, not overrides the client sent.