Qwen3.8 125B (6B active) Flash-Next
on 2× NVIDIA RTX 3080 20GB · ExLlamaV3 · 160,000 ctx
Summary
User reports CPU-offloaded inference with 128 GB of system RAM, running 3.2x faster prefill and 2x faster decode than llama.cpp.
User also tested GLM 5.3 Flash with 3.05 EXL3, which ran 2x slower in decode than llama.cpp.
Decode speeds warm up over time.