Question 1

Can the AMD Ryzen AI Max (Strix Halo) run mixtral 8x7B MoE?

Accepted Answer

mixtral 8x7B MoE needs about 26.5GB working set (weights 26GB + KV cache 0.5GB at 4k context). The AMD Ryzen AI Max (Strix Halo) offers ~30GB usable — verdict: tight. 26.5 of 30 GB usable — keep context modest

Question 2

How fast is mixtral 8x7B MoE on the AMD Ryzen AI Max (Strix Halo)?

Accepted Answer

~39–56 tok/s (active-expert estimate) on the AMD Ryzen AI Max (Strix Halo). computed roofline: 256 GB/s × 0.60–0.85 efficiency window / 3.9GB (Q4_K_M) — bands, never points. MoE: file is 26GB (that decides fit) but only ~1.05B of experts activate per token (~3.9GB streamed) — band below is the active-expert estimate, optimistic; community MoE rows run several× the naive bandwidth math

Question 3

What should I run mixtral 8x7B MoE on instead?

Accepted Answer

Mac mini M5 Pro (64GB) runs it fully ($1669).

Can the AMD Ryzen AI Max (Strix Halo) run mixtral 8x7B MoE?

Run mixtral 8x7B MoE on instead