Wësche(@WescheNex1q):Take two: Mac Studio m4 Max recipe Qwen3.8-Flash-Next update Average 83tok/s • MTP off→MTP3 weighted decode: 36.64→68.31 tok/s (1.86×) • MTP3→MTP6 5,999-token decode: 70.44→83.06 tok/s (+17.9%) • TrueScore: 91.8→91.9 •256k context Deployment: https://t.co/sjQrX8ZK8D

Wësche

@WescheNex1q

Day time artist and night time AI enthusiast. Building & benchmarking frontier LLMs on 4x DGX Spark clusters + Mac. Creator of Vesica Studio. Houston

参加 January 2013

637 フォロー中 2.4K ファン

Wësche@WescheNex1q

2026.08.30 20:57

Take two: Mac Studio m4 Max recipe Qwen3.8-Flash-Next update Average 83tok/s • MTP off→MTP3 weighted decode: 36.64→68.31 tok/s (1.86×) • MTP3→MTP6 5,999-token decode: 70.44→83.06 tok/s (+17.9%) • TrueScore: 91.8→91.9 •256k context Deployment: