Qwen3.8 27B
on 2× Mixed NVIDIA/AMD GPUs (one RTX 3060 12GB and one Radeon 8060S; two GPUs total; RAM unknown) · llama.cpp
Summary
User reports Qwen3.8-27B UD-IQ3_XXS at 19.6 t/s generation and 658.5 t/s prompt processing on one NVIDIA RTX 3060 12 GB plus one Radeon 8060S integrated in a Ryzen AI Max+ 395.
Setup is llama.cpp native llama-bench with heterogeneous CUDA and Vulkan layer stages across the two GPUs.
The headline prompt and generation figures come from separate tests, not a paired 4096-input/64-output request; concurrency was 1, and the source reports 27.32B parameters, 10.17 GiB model size and 3.06 bpw.