Benchmark result
gemma4:latest — 74.2 tok/s
Measured with Ollama 0.30.6 on September 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; the frame only adds a line that tells this page how tall it is.
How this run compares
gemma4:latest on other hardware
- 74.4tok/s62.2Unknown hardware · Q4_K_M
- 74.2tok/s54.8Unknown hardware · Q4_K_Mthis run
- 68.1tok/s58.0AMD Radeon RX 9070/9070 XT/9070 GRE · Q4_K_M
Reproduce this run
toolOllama 0.30.6
modelgemma4:latest (Q4_K_M)
context8,192
clientv0.4.30+97
Set those in Ollama, then:
llm-benchmark benchmark --model "gemma4:latest" --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.