Qwen3.8 27B
on NVIDIA RTX 5080 · llama.cpp · 65,536 ctx
Sep 7, 2026
Use cases
coding
Summary
User reports a first tuning attempt with selective FFN offload to CPU improving speed over whole-layer offload.
True Q4_K_M runs at 13.2 tok/s near 50-61K context.
MTP is worse at deep context. Coding quality improved over IQ3.