Qwen3.8 27B
on AMD RX 7800 XT 16GB · llama.cpp · 100,096 ctx
Sep 29, 2026
Summary
User reports Qwen 3.8 27B at ~30 t/s decode on an RX 7800 XT 16GB.
Setup is llama.cpp with Vulkan, UD-IQ4_XS GGUF quant, q8_0/q5_1 KV cache, 100096 context, no MTP, single request, full GPU offload.
User shares the setup because many believe Qwen 3.8 27B is infeasible on 16GB VRAM.