can it run
Comfortably. 128GB of memory against a 24GB working set leaves headroom for context, the OS, and anything else you're running.
weights 18.6GB + KV cache 0.38GB at 4k context vs ~126GB usable → full. 19.0 GB needed of 126 GB usable — headroom for context
computed roofline: 273 GB/s × 0.25–0.65 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
| model file | 18.6GB (GGUF Q4_K_M) |
| minimum memory | 24GB working set |
| this machine | 128GB unified |
| params | 30B-A3B MoE |
| license | apache-2.0 |
| price | $4299 |
easy run: ollama pull qwen3-coder:30b
runs with: ollama · llama.cpp · koboldcpp · lm studio
→ ASUS ExpertCenter Pro ET900N G3 (GB300) — this model on the biggest machine
→ rtx-5090 — the next step up from this machine's GPU