Qwen3.8 27B
on 2× NVIDIA RTX 5080 · Ollama · 65,536 ctx
Summary
User reports Qwen3.8 27B at about 40 tokens/second on an RTX 5080 plus RTX 5070, with MTP disabled.
Setup is Ollama with Q8_0 weights and 128k of context; the vision encoder and MTP were turned off to fit the split across the two cards.
With MTP enabled at 64k context the user sees about 54 tokens/second. They ask whether Ollama's per-GPU buffer can be lowered, having had no luck with LLAMA_ARG_FIT_TARGET, or whether to switch to llama.cpp.