Benchmark result
gemma4:31b on NVIDIA RTX 3500 Ada Generation Laptop GPU — 4.6 tok/s
Measured with Ollama 0.40.15 on November 12, 2026.
Support llm-bench.io
llm-bench.io is free. If it helped you, I'd appreciate your support to cover the infrastructure costs.
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
3rd fastest of 5 runs of this model on NVIDIA RTX 3500 Ada Generation Laptop GPU · median 4.6 tok/s.
sort
- 14.6tok/s77.0Ollama · Q4_K_M
- 24.6tok/s78.5Ollama · Q4_K_M
- 34.6tok/s78.0Ollama · Q4_K_Mthis run
- 44.5tok/s70.8Ollama · Q4_K_M
- 54.4tok/s75.9Ollama · Q4_K_M
Reproduce this run
toolOllama 0.40.15
modelgemma4:31b (Q4_K_M)
context8,192
samplingtemperature 1 · top_p 0.95 · top_k 64
clientv0.4.99+102
Set those in Ollama, then:
llm-benchmark benchmark --model "gemma4:31b" --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.