Benchmark result
qwen3.8-agent:latest on Apple M4 Pro — 18.7 tok/s
Measured with Ollama 0.32.13 on August 20, 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.
Reproduce this run
toolOllama 0.32.13
modelqwen3.8-agent:latest (nvfp4)
context32,768
clientv0.4.39+97
Set those in Ollama, then:
llm-benchmark benchmark --model "qwen3.8-agent: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.