Question 1

Can the NVIDIA Titan Xp 12GB run qwen3-coder 30B-A3B MoE?

Accepted Answer

qwen3-coder 30B-A3B MoE needs about 18.98GB working set (weights 18.6GB + KV cache 0.38GB at 4k context). The NVIDIA Titan Xp 12GB offers ~12GB usable — verdict: no. 19.0 GB vs 12 GB usable — does not fit

Question 2

How fast is qwen3-coder 30B-A3B MoE on the NVIDIA Titan Xp 12GB?

Accepted Answer

~82–150 tok/s (active-expert estimate) on the NVIDIA Titan Xp 12GB. computed roofline: 547.6 GB/s × 0.28–0.50 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-coder 30B-A3B MoE on instead?

Accepted Answer

Tesla V100 32GB (used) runs it fully ($640).

Can the NVIDIA Titan Xp 12GB run qwen3-coder 30B-A3B MoE?

Run qwen3-coder 30B-A3B MoE on instead