netrunner(@plotarmordev):Got temporary access to a Mac Studio M5 Ultra. Barely optimized, Qwen 3.8 Flash Next runs at 85.9 tok/s and 6085 tok/s prefill on long prompts. A 2x DGX Spark recipe gets 52.1 tok/s single stream and about 2960 tok/s prefill on 16k–64k prompts. Already ahead of 2x Spark, but I was expecting a much much better baseline…

netrunner

@plotarmordev

Cofounder & engineer. Running local AI, building things with it, and sharing what I learn.

Joined April 2022

675 Following 7.1K Followers

netrunner@plotarmordev

2026.09.25 03:09

Got temporary access to a Mac Studio M5 Ultra. Barely optimized, Qwen 3.8 Flash Next runs at 85.9 tok/s and 6085 tok/s prefill on long prompts. A 2x DGX Spark recipe gets 52.1 tok/s single stream and about 2960 tok/s prefill on 16k–64k prompts. Already ahead of 2x Spark, but I was expecting a much much better baseline…