Benchmark result
iq3_s on Apple M5 Ultra — 140.2 tok/s
Measured with iq3_s manual on October 28, 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
Reproduce this run
tooliq3_s manual
modeliq3_s
context65,536
clientv0.4.98+102
Set those in iq3_s, then:
llm-benchmark benchmark --model "iq3_s" --tool "iq3_s"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.