Qwen3.8 27B
on NVIDIA RTX 5090 · llama.cpp
Oct 7, 2026
Use cases
codingmathagentictool-usevision
Summary
User reports Qwen3.8-27B at 94 t/s on an RTX 5090.
Setup is llama.cpp with IQ4_XS GGUF quantization, single stream, flash attention on, thinking mode sampling.
With MTP speculative decoding it reaches 147 t/s (1.57x) and with DFlash2 167 t/s (1.78x). The model is 13.1 GB at 3.84 bits per weight.