Qwen3.8 27B
on NVIDIA RTX 4090 · llama.cpp · 92,160 ctx
Sep 7, 2026
Summary
User reports Qwen3.8-27B on an RTX 4090, with throughput ranging from 44 t/s to 134 t/s and no RAM spilling.
Setup includes an mmproj file for vision.
on NVIDIA RTX 4090 · llama.cpp · 92,160 ctx