AMD Max+ Pro 495 benchmarks are starting to trickle out.
This user got their single 192GB AMD Minisforum mini PC running gpt-oss 120B MXFP4 with llama.cpp at 55.7 tps.
Setup
đ§ gpt-oss 120B
đž 192GB LPDDR5X-8533 unified memory
đŽ Radeon 8065S
⥠55.7 tps decode
đ 1,135 tps prefill
And deeper into context, at the source's ~32K test depth
⥠42.3 tps decode
đ 385 tps prefill
This is why these 192GB unified-memory machines could be a big deal for Local AI.
Link in ALT