Qwen3.8 27B Swift
on NVIDIA RTX 5090 · llama.cpp
Oct 3, 2026
Use cases
coding
Summary
User reports Qwen3.8 27B Swift at 143 tok/s decode and 2840 tok/s prefill on an RTX 5090.
Setup is llama.cpp with Q6_K quantization.
The figures come from a coding prompt asking for an HTML/JS calculator, which produced a working result in 1 minute 10 seconds; the user calls this the ceiling after two days of trials.