Qwen3.8 125B (6B active) Flash-Next
on 2× NVIDIA DGX Spark · 2,048 ctx
Use cases
coding
Summary
User reports Qwen3.8-Flash-Next at about 86 tok/s decode on 2x DGX Spark, with prefill improved to 2892 tok/s at pp2048 c1.
Setup is a 2x Spark tensor-parallel recipe (v2.2.0) with a 16K cold TTFT of 5.49 s; the 1x release (v2.4.0) decodes about 60 tok/s and prefills 1916 tok/s.
Prefill gains come from reading GDN prefill inputs as views and running one projection as a single BF16 GEMM; decode is unchanged and both releases passed the same quality gate.