Summary
User reports running Qwen3.8-Flash-Next oQ4 through oMLX on a Mac Studio M3 Ultra 96GB at around 60-70 t/s decode.
Setup is oMLX with an MLX oQ4 quant of the model.
The figure is given as a range, and the user asks whether the Splash engine running a GGUF model could beat MLX native decode speed, and about the quality trade-offs.