llamaperf

Qwen3.8 125B (6B active) Flash-Next

on AMD Strix Halo 128GB · libosmos

Tone: positiveAMD hardware
Nov 9, 2026
Throughput
27.1 t/s gen · 873.0 tokens/s prompt processing (prefill)Prompt processing is how fast the input is read, not how long you wait for the first word. How to measure time to first token.
Quant
ud-iq3_xxs (GGUF)
System RAM
128 GB
VRAM reported
113 GB

Summary

User reports Qwen3.8-Flash-Next at 27.1 tok/s decode (45.6 tok/s with drafting) on a single AMD Strix Halo 128GB in performance mode with 113GB RAM dedicated to the GPU. Setup is the libosmos engine with the ud-iq3_xxs pack; prompt processing runs 873/822/811/709 tok/s at 2k/8k/16k/64k steps. The engine was tuned at a 70W power envelope. The post also lists DeepSeek V4.1 Flash 1017 decode of 19.5/42.5, 17.5/35.4 and 14.4/26.5 tok/s plain/drafted for ud-iq1_s, ud-iq1_m and ud-iq2_xxs, with 2k/8k prompt speeds of 380/534, 373/519 and 316/429 tok/s.

Compare this run

Medians of plain runs: one device, one request, no speculative decoding, the whole model in the device's memory. The report above is one setup, so read it beside them and not as one of them.

Qwen3.8 125B · 6B active at 4-bit by hardware

Bars are medians on one scale, 0 to 232.0 tokens/s. Each dot is one run and opens its report. Press ▶ to watch text arrive at a row's speed.

Models most run on the AMD Strix Halo 128GB

Bars are medians on one scale, 0 to 77.0 tokens/s. Each dot is one run and opens its report. Press ▶ to watch text arrive at a row's speed.

Everything reported on the AMD Strix Halo 128GB →Every Qwen3.8 report →Estimate Qwen3.8 on this card →