can it run
Comfortably. 80GB of memory against a 18GB working set leaves headroom for context, the OS, and anything else you're running.
weights 14GB + KV cache 0.19GB at 4k context vs ~80GB usable → full. 14.2 GB needed of 80 GB usable — headroom for context
computed roofline: 2039 GB/s × 0.46–0.76 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
| model file | 14GB (GGUF Q4_K_M) |
| minimum memory | 18GB working set |
| this machine | 80GB HBM2e, 2 TB/s |
| params | 20B MoE |
| license | apache-2.0 |
| price | $23000 |
easy run: ollama pull gpt-oss:20b
runs with: ollama · llama.cpp · koboldcpp · lm studio
→ ASUS ExpertCenter Pro ET900N G3 (GB300) — this model on the biggest machine
→ rtx-pro-6000 — the next step up from this machine's GPU
NVIDIA (used market) ↗ · Amazon ↗