can it run
No. 16GB of memory can't hold the 24GB working set this model needs. A smaller quant or a bigger machine is required.
weights 18.6GB + KV cache 0.38GB at 4k context vs ~16GB usable → offload-partial. 19.0 GB vs 16 GB usable — partial CPU offload, expect large speed loss
computed roofline: 448 GB/s × 0.46–0.76 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 | 16GB GDDR7, 448 GB/s |
| params | 30B-A3B MoE |
| license | apache-2.0 |
| price | $480 |
easy run: ollama pull qwen3-coder:30b
runs with: ollama · llama.cpp · koboldcpp · lm studio
→ Mac mini M5 Pro (64GB) — cheapest machine that runs it ($1669)
→ every model the RTX 5060 Ti 16GB can run — full list
→ rtx-5070-ti — the next step up from this machine's GPU
Amazon ↗ · Amazon ↗ (affiliate)