can it run
Yes, but close to the edge. 32GB against a 29GB working set: it runs, with little room for long context windows or other processes.
weights 23GB + KV cache 2GB at 4k context vs ~30GB usable → tight. 25.0 of 30 GB usable — keep context modest
computed roofline: 120 GB/s × 0.80–1.00 efficiency window / 23.0GB (Q4_K_M) — bands, never points.
| model file | 23GB (GGUF Q4_K_M) |
| minimum memory | 29GB working set |
| this machine | 32GB unified |
| params | dev fp8 |
| license | flux-dev-nc / apache schnell |
| price | $999 |
easy run: no stock runtime yet
→ Mac mini M5 Pro (64GB) — cheapest machine that runs it ($1669)
→ ASUS ExpertCenter Pro ET900N G3 (GB300) — this model on the biggest machine