Qwen 3.8-Flash-Next / Nathanw v0.7.5 / PP512 TG32 at depth 32768

on AMD Strix Halo 128GB · llama.cpp Nathanw v0.7.5 / dff60048 / Vulkan RADV

Oct 13, 2026

Throughput

23.6 t/s gen · 321.8 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)

MTP (Multi-Token Prediction)

off

System RAM

128 GB

Summary

User reports Qwen3.8-Flash-Next at 23.6 t/s generation and 321.8 t/s prompt processing on an AMD Strix Halo 128GB machine. Setup is llama.cpp with the Unsloth UD-Q4_K_XL GGUF, offloaded fully to the iGPU, at a prepared depth of 32768 with no MTP. The 321.8/23.6 figures come from a PP512/TG32 run with Nathanw v0.7.5, compared against stock pr28243 at 215.6/20.3 tokens/s; TG32 and TG8 results are not cross-paired.