Benchmark result
gemma4:31b-coding-mtp-bf16 on Apple M5 Max — 0.0 tok/s
Measured with Ollama 0.23.2 on May 23, 2026.
Reproduce this run
toolOllama 0.23.2
modelgemma4:31b-coding-mtp-bf16
context65,536
clientv0.4.22+97
Set those in Ollama, then:
llm-benchmark benchmark --model "gemma4:31b-coding-mtp-bf16" --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.