Qwen-AgentWorld-35B-A3B / ROCm / PP512 TG128 / depth 1024 / KV f16
on AMD Strix Halo 128GB · llama.cpp build 1 / a66d5058 / ROCm
Summary
User reports Qwen-AgentWorld-35B-A3B UD-Q4_K_XL at 51.2 t/s generation and 974.3 t/s prompt processing on an AMD Strix Halo 128GB machine.
Setup is llama.cpp build 1 (a66d50588b105ef81fe6c2debd19440f5a8ab97a) on ROCm with f16/f16 KV cache at depth 1024, one Radeon 8060S GPU.
The headline figures are separate synthetic tests, PP512 and TG128, not one request; no TTFT was measured, and each cell has a single repetition.