Qwen3.8 125B (6B active) Flash-Next
on Unknown GPU · Strata · 176,128 ctx
Use cases
long-contexttool-use
Summary
User reports Qwen3.8 Flash-Next at 36 t/s generation and 340 t/s prefill on 8GB VRAM and 32GB RAM.
Setup is Strata with QFN Q_2 quant and q4_0 KV cache, 176128 context, 2000 experts cached, MTP disabled.
User says this is the best model they have run on this hardware, with no tool call issues or looping, and ran past 3 compactions at 192k context with fewer cached experts.