Qwen3.8 125B (6B active) Flash-Next

on 4× NVIDIA RTX 3090 · llama.cpp · 10,000 ctx

Sep 7, 2026

Throughput

55.0 t/s gen

Quant

Q4_K_XL (GGUF)

VRAM reported

24 GB

Summary

User reports 55 t/s on 4x RTX 3090 with Qwen3.8-Flash-Next-UD.