Qwen3.8 27B
on 2× NVIDIA RTX 3090 · llama.cpp
Oct 5, 2026
Use cases
summarization
Summary
User reports Qwen3.8 27B at 38.1 t/s generation and 1263 t/s prefill on 2x RTX 3090, asking whether NVLink would improve performance over a better motherboard.
Setup is llama.cpp b10586 (CUDA) behind llama-swap on Windows 11, with a Ryzen 7 5800X3D and 64GB DDR4. Cold load took 24s.
At 28k context the run gave 1250 t/s prefill and 36.2 t/s generation; at 85k context 901 t/s prefill and 28.9 t/s generation. User also runs nightly data classification jobs and asks whether prefill speed would benefit.