Benchmark result
gemma4:e4b on Apple M4 Pro — 54.3 tok/s
Measured with Ollama 0.32.5 on July 29, 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
2nd fastest of 2 runs of this model on Apple M4 Pro · median 54.8 tok/s.
sort
- 155.4tok/s62.8Ollama · Q4_K_M
- 254.3tok/s58.3Ollama · Q4_K_Mthis run
Reproduce this run
toolOllama 0.32.5
modelgemma4:e4b (Q4_K_M)
context8,192
clientv0.4.30+97
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.