Benchmark result
ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF:IQ3_S on Apple M4 Pro — 34.0 tok/s
Measured with Splash manual on October 15, 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
ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF:IQ3_S on other hardware
Reproduce this run
toolSplash manual
modelISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF:IQ3_S
context262,144
thinkingon
clientv0.4.93+102
Set those in Splash, then:
llm-benchmark benchmark --model "ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF:IQ3_S" --tool "Splash"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.