Qwen3.5 4B

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

Oct 14, 2026

Throughput

48.5 t/s gen · 1388.9 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)

System RAM

128 GB

Summary

User reports Qwen3.5-4B-UD-Q4_K_XL at 48.5 t/s generation and 1388.9 t/s prompt processing on an AMD Strix Halo 128GB machine. Setup is llama-bench build b8171 with the Vulkan backend, ngl 99, and the UD-Q4_K_XL quant, on a Radeon 8060S (RADV GFX1151) iGPU. The stored rates are rounded to 0.1 t/s from native PP512 1388.87 +/- 10.68 t/s and TG128 48.53 +/- 0.65 t/s, separate synthetic phases rather than a same-request pair.