Qwen 3.8-Flash-Next-Uncensored / Gufo AR / mixed-long independent medians

on AMD Strix Halo 128GB · Gufo eb915840 / ROCm HIP / autoregressive

Oct 13, 2026

Throughput

23.4 t/s gen · 1263.5 tokens/s prompt processing (prefill)Prompt processing measures input prefill speed; it does not tell you the time to first token.

Quant

Q4 Mix (Q4_K/Q5_1/IQ4_NL/Q8_0) (GGUF)

MTP (Multi-Token Prediction)

off

System RAM

128 GB

Summary

User reports Qwen3.8-Flash-Next-Uncensored at 23.4 t/s generation and 1263.5 t/s prompt processing on an AMD Strix Halo 128GB system. Setup is the Gufo runtime over ROCm/HIP with a Q4 Mix GGUF (Q4_K/Q5_1/IQ4_NL/Q8_0) and autoregressive decoding, MTP off, one GPU. The figures are medians of three mixed-long requests at 10,583 input and 128 output tokens each, with all prompts uncached; client-observed TTFT median was 8.436 seconds.