Qwen3.8 125B (6B active) Flash-Next
on 3× NVIDIA RTX 3090 · ExLlamaV3 · 262,144 ctx
Sep 20, 2026
Summary
User reports Qwen3.8 Flash-Next at 80 t/s generation and 1500 t/s prefill on 3x RTX 3090 with 128GB DDR4.
Setup is ExLlamaV3 with an exl3 3bpw quant at 262,144 context, with vision and speculative decoding enabled.
A single RTX 5090 with 128GB DDR4 reached 29 t/s generation at the same 1500 t/s prefill and 262k context. User plans to test 4bpw later and says ExLlamaV3 is replacing vLLM and llama.cpp for this model.