Q: How fast is qwen3 30B-A3B MoE on the Intel Arc B60 (Battlemage Pro)?

~150–190 tok/s (active-expert estimate) on the Intel Arc B60 (Battlemage Pro). computed roofline: 456 GB/s × 0.60–0.78 efficiency window / 1.9GB (Q4_K_M) — bands, never points. MoE: file is 18.6GB (that decides fit) but only ~3B of experts activate per token (~1.9GB streamed) — band below is the active-expert estimate, optimistic; community MoE rows run several× the naive bandwidth math

Question 1

Can the Intel Arc B60 (Battlemage Pro) run qwen3 30B-A3B MoE?

Accepted Answer

qwen3 30B-A3B MoE needs about 18.98GB working set (weights 18.6GB + KV cache 0.38GB at 4k context). The Intel Arc B60 (Battlemage Pro) offers ~24GB usable — verdict: full. 19.0 GB needed of 24 GB usable — headroom for context

Question 2

How fast is qwen3 30B-A3B MoE on the Intel Arc B60 (Battlemage Pro)?

Accepted Answer

~150–190 tok/s (active-expert estimate)

computed roofline: 456 GB/s × 0.60–0.78 efficiency window / 1.9GB (Q4_K_M) — bands, never points.

MoE: file is 18.6GB (that decides fit) but only ~3B of experts activate per token (~1.9GB streamed) — band below is the active-expert estimate, optimistic; community MoE rows run several× the naive bandwidth math

Question 3

What should I run qwen3 30B-A3B MoE on instead?

Accepted Answer

Mac mini M4 (32GB) runs it fully ($999).

Can the Intel Arc B60 (Battlemage Pro) run qwen3 30B-A3B MoE?

Run qwen3 30B-A3B MoE on instead