Qwen3.5 35B (3B active)

on AMD Strix Halo 128GB · llama.cpp b8171 / c17dce4f / Vulkan RADV

Oct 14, 2026

Throughput

31.8 t/s gen · 747.7 tokens/s prompt processing (prefill)Prompt processing measures input prefill speed; it does not tell you the time to first token.

Quant

UD-Q8_K_XL (GGUF)

System RAM

128 GB

Summary

User reports Qwen3.5 35B-A3B at 31.8 t/s generation and 747.7 t/s prompt processing on an AMD Strix Halo 128GB machine. Setup is llama-bench build b8171 with the Vulkan backend, UD-Q8_K_XL quant, ngl 99, and a Radeon 8060S Graphics (RADV GFX1151) device. The rates are separate synthetic phases: PP512 at 747.72 +/- 44.81 t/s and TG128 at 31.83 +/- 0.03 t/s, not a same-request prompt/output pair.