Benchmark result
gemma4:e4b on Apple M5 Pro — 126.1 tok/s
Measured with Ollama 0.40.13 on November 1, 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; the frame only adds a line that tells this page how tall it is.
How this run compares
gemma4:e4b on other hardware
Reproduce this run
toolOllama 0.40.13
modelgemma4:e4b (nvfp4)
context65,536
samplingtemperature 1 · top_p 0.95 · top_k 64
clientv0.4.98+102
Set those in Ollama, then:
llm-benchmark benchmark --model "gemma4:e4b" --tool "Ollama"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.