llamaperf
Nov 5, 2026
Throughput
38.0 t/s gen · 480.0 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-IQ1_S (GGUF)
System RAM
128 GB

Summary

User reports DeepSeek-V4.1-Flash 1017 at up to 38 tok/s decode and over 480 tok/s prompt processing on a single Strix Halo 128GB (Ryzen AI MAX+ 395, Radeon 8060S / gfx1151). Setup is the libosmos engine with unsloth UD-IQ1_S weights plus an MXFP8 engram, with drafting enabled for the decode figure. The figures are stated as ceilings ("up to"), and a huihui abliteration is said to be available through the engine.

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.

DeepSeek V4.1 Flash 552B · 16B active at 3-bit by hardware

Bars are medians on one scale, 0 to 73.4 tokens/s. 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 DeepSeek V4.1 Flash report →Estimate DeepSeek V4.1 Flash on this card →