Benchmark result
google/gemma-4-31b on Apple M5 Max — 15.1 tok/s
Measured with LM Studio on October 30, 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 4 runs of this model on Apple M5 Max · median 15.2 tok/s.
sort
- 120.0tok/s72.0LM Studio
- 215.2tok/s78.1LM Studio · Q8_0
- 315.1tok/s75.4LM Studio · Q8_0this run
- 414.9tok/s75.1LM Studio
google/gemma-4-31b on other hardware
Reproduce this run
toolLM Studio
modelgoogle/gemma-4-31b (Q8_0)
context8,192
clientv0.4.98+102
Set those in LM Studio, then:
llm-benchmark benchmark --model "google/gemma-4-31b" --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.