Q: How fast is qwen3 235B-A22B MoE on the AMD Instinct MI430X 432GB?

~490–790 tok/s (active-expert estimate) on the AMD Instinct MI430X 432GB. computed roofline: 23300 GB/s × 0.28–0.45 efficiency window / 13.3GB (Q4_K_M) — bands, never points. MoE: file is 142GB (that decides fit) but only ~22B of experts activate per token (~13.3GB streamed) — band below is the active-expert estimate, optimistic; community MoE rows run several× the naive bandwidth math

Question 1

Can the AMD Instinct MI430X 432GB run qwen3 235B-A22B MoE?

Accepted Answer

qwen3 235B-A22B MoE needs about 142.73GB working set (weights 142GB + KV cache 0.73GB at 4k context). The AMD Instinct MI430X 432GB offers ~432GB usable — verdict: full. 142.7 GB needed of 432 GB usable — headroom for context

Question 2

How fast is qwen3 235B-A22B MoE on the AMD Instinct MI430X 432GB?

Accepted Answer

~490–790 tok/s (active-expert estimate)

computed roofline: 23300 GB/s × 0.28–0.45 efficiency window / 13.3GB (Q4_K_M) — bands, never points.

MoE: file is 142GB (that decides fit) but only ~22B of experts activate per token (~13.3GB streamed) — band below is the active-expert estimate, optimistic; community MoE rows run several× the naive bandwidth math

Question 3

What should I run qwen3 235B-A22B MoE on instead?

Accepted Answer

ASUS ExpertCenter Pro ET900N G3 (GB300) runs it fully ($60000).

Can the AMD Instinct MI430X 432GB run qwen3 235B-A22B MoE?

Run qwen3 235B-A22B MoE on instead