Qwen3.8 125B (6B active) Flash-Next
on NVIDIA T4 16GB · ik_llama.cpp · 262,144 ctx
Use cases
coding
Summary
User reports Qwen3.8-Flash-Next, 180B total with 6B active across 512 experts, generating 17.6 t/s on short prompts and 16.1 t/s at 12.5K context.
Non-expert weights run on a T4 using 4606 MiB, with the experts held in host RAM.
Prompt processing reaches 159.6 t/s on a cold 12.5K prompt. User reports solid refactor and coding performance, and finds it less verbose than Opus.