Qwen3.6 35B (3B active)
on Intel Arc B390 · llama.cpp
Summary
User reports Qwen3.6-35B-A3B at 33-36 t/s generation and 145 t/s prompt processing on an Intel Arc B390 integrated GPU after tuning llama.cpp.
Setup is llama.cpp 0.5.0-dev (build 158) with Vulkan backend, Q4_K_M quant, 30 GiB unified memory and 23.7 GiB device memory, MTP speculative decoding with spec-draft-n-max 2, batch and ubatch 2048, CPU_MOE disabled.
Before the changes the same setup gave 15-17 t/s generation and 130 t/s prompt processing; llama-bench reports 38.7 t/s generation.