Q: How fast is gpt-oss 20B MoE on the Intel Arc B60 (Battlemage Pro)?

~130–170 tok/s (active-expert estimate) on the Intel Arc B60 (Battlemage Pro). computed roofline: 456 GB/s × 0.60–0.78 efficiency window / 2.1GB (Q4_K_M) — bands, never points. MoE: file is 14GB (that decides fit) but only ~3B of experts activate per token (~2.1GB 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 gpt-oss 20B MoE?

Accepted Answer

gpt-oss 20B MoE needs about 14.19GB working set (weights 14GB + KV cache 0.19GB at 4k context). The Intel Arc B60 (Battlemage Pro) offers ~24GB usable — verdict: full. 14.2 GB needed of 24 GB usable — headroom for context

Question 2

How fast is gpt-oss 20B MoE on the Intel Arc B60 (Battlemage Pro)?

Accepted Answer

~130–170 tok/s (active-expert estimate)

computed roofline: 456 GB/s × 0.60–0.78 efficiency window / 2.1GB (Q4_K_M) — bands, never points.

MoE: file is 14GB (that decides fit) but only ~3B of experts activate per token (~2.1GB streamed) — band below is the active-expert estimate, optimistic; community MoE rows run several× the naive bandwidth math

Question 3

What should I run gpt-oss 20B MoE on instead?

Accepted Answer

Tesla P40 (24GB, used) runs it fully ($290).

Can the Intel Arc B60 (Battlemage Pro) run gpt-oss 20B MoE?

Run gpt-oss 20B MoE on instead