llamaperf

Unknown family

on AMD Strix Halo 128GB · Gufo · 16,384 ctx

Tone: mixedAMD hardware
Nov 9, 2026
Throughput
60.9 t/s gen · 1888.0 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.
System RAM
128 GB

Summary

User benchmarks Gufo on a Strix Halo 128GB mini PC (Nimo 395), splitting work between GPU and NPU with FCLK locked at 2000 MHz. At 16k context, GPU-only prefill reaches 1888 t/s and GPU+NPU 2080 t/s without MTP; with MTP the figures are 1812 t/s and 2002 t/s, roughly +10% either way. Short-context decode stays at 60.9 t/s with or without the NPU. Higher 16k decode numbers in some GPU+NPU+MTP runs are not treated as a pure NPU speedup because acceptance rate and output change. The model is not named.

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.

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 →