llamaperf

Minimax M2.1 IQ4_XS / ROCm b7822 / native PP256 and separate TG256

on AMD Radeon Graphics gfx1151 (marketing SKU and installed RAM unreported) · llama.cpp b7822 / 8f91ca54e / ROCm 7.1.1

Oct 14, 2026
Throughput
28.9 t/s gen · 147.6 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
IQ4_XS (GGUF)
Flash Attention
on

Summary

User reports Minimax M2.1 at 28.9 t/s generation and 147.6 t/s prompt processing on an AMD Radeon Graphics gfx1151 device. Setup is llama-bench on ROCm 7.1.1 with IQ4_XS, ngl=999, FA=1, and dev=ROCm0, selecting one GPU. The native figures are PP256 147.63 +/- 2.44 and TG256 28.92 +/- 0.21; exact context depth, CPU threads, and repetitions are unknown.

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.

Every Minimax M2.1 report →