Tag
Benchmarks of Gemma 4 and Qwen 3.6 MoE models on AMD 6800H iGPU using llama.cpp Vulkan backend show that MoE models and lower-bit quantization (Q4_0) provide the best performance, while Q8_0 is too slow for large models.
User seeks advice on running llama.cpp with Gemma 4 E2B on an Intel N100 mini PC, asking whether to use CPU or iGPU and which backend to target.
xdna-top is a terminal monitor that shows both NPU and iGPU activity on Ryzen AI Max/Strix Halo systems, providing an honest view of NPU counter deltas instead of fake utilization percentages.