MiniMax M2.7 / Vulkan RADV native PP512/TG128

on AMD Strix Halo 128GB · llama.cpp / Vulkan RADV / build unknown

Oct 13, 2026

Throughput

27.0 t/s gen · 181.0 tokens/s prompt processing (prefill)Prompt processing measures input prefill speed; it does not tell you the time to first token.

Quant

UD-IQ4_XS (GGUF)

Flash Attention

System RAM

128 GB

Summary

User reports MiniMax-M2.7 at 27 t/s generation and 181 t/s prompt processing on a single Radeon 8060S iGPU in an AMD Strix Halo 128GB system. Setup is llama.cpp with the Unsloth UD-IQ4_XS quant, full offload, batch 2048 and flash attention, using the RADV backend. The rates are separate llama-bench pp512 and tg128 microbenchmarks, not one end-to-end request; repetition count, context allocation and cache type are not published.