Qwen-AgentWorld-35B-A3B / Vulkan RADV / PP512 TG128 / depth 1024 / KV f16

on AMD Strix Halo 128GB · llama.cpp b9747 / d6d89958 / Vulkan RADV

Oct 14, 2026

Throughput

60.0 t/s gen · 1085.7 tokens/s prompt processing (prefill)Prompt processing measures input prefill speed; it does not tell you the time to first token.

Quant

UD-Q4_K_XL (GGUF)

KV cache

F16

Flash Attention

MTP (Multi-Token Prediction)

off

System RAM

128 GB

Summary

User reports Qwen-AgentWorld-35B-A3B UD-Q4_K_XL at 60 t/s generation and 1085.7 t/s prompt processing on an AMD Strix Halo 128GB machine. Setup is llama.cpp build 9747 with Vulkan RADV, f16/f16 KV cache at depth 1024, one Radeon 8060S GPU. The headline figures are separate synthetic tests, not one request: PP512 1085.717646 t/s and TG128 60.011904 t/s, each with a single repetition.