llamaperf

Qwen3.8 27B

on AMD Strix Halo 128GB · Gufo · 262,144 ctx

Tone: positiveAMD hardware
Nov 6, 2026
Throughput
24.0 t/s gen · 450.0 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-Q4-K-XL (GGUF)

Use cases

coding

Summary

User reports Qwen3.8-27B at 24 t/s generation and 450 t/s prefill at 262,144 context on a Strix Halo box. Setup is recent Gufo builds with UD-Q4-K-XL weights and DFLASH speculative decoding, using around 40GB of memory. User says speed stays steady as context grows, unlike earlier llama.cpp and MTP attempts that fell to single digits. They ask about automatically switching between QFN for planning and coding and the 27B for memory-heavy builds, noting QFN is faster but uses about 102GB of RAM.

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 27B at 4-bit by hardware

Bars are medians on one scale, 0 to 94.0 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 →