Qwen3 30B (3B active)
on AMD Strix Halo 128GB · llama.cpp · 49,152 ctx
Use cases
long-context
Summary
User reports Qwen3 30B-A3B at 58.57 t/s decode and 920 t/s prefill on an AMD Strix Halo 128GB at 12,001 tokens of context.
Setup is llama.cpp with the Q4_K_M GGUF over Vulkan, 49,152-token context, 96 GB of the 128 GB LPDDR5X allocated to the iGPU.
At 48,001 tokens prefill drops to 254 t/s and decode to 30.06 t/s; at 11 tokens prefill is 122 t/s and decode 88.40 t/s. ROCm gives about 28 percent better prefill while Vulkan gives about 13 percent better decode.