Qwen3.8 125B (6B active) Flash-Next
on 3× NVIDIA RTX 5070 Ti · llama.cpp · 256,000 ctx
Sep 7, 2026
Summary
User reports the AtomicChat build of Qwen3.8-Flash-Next running a full 256K context on 96 GB RAM and 40 GB VRAM, at 22 t/s.
The build splits the n-gram table to SSD. The user previously ran unsloth quants, which crashed at around 60K context and were slower at 12-14 t/s.
The AtomicChat build handles a 217K token conversation without crashing. Prefill takes about 18 minutes for 220K context.