can it run
Comfortably. 32GB of memory against a 22GB working set leaves headroom for context, the OS, and anything else you're running.
weights 17GB + KV cache 2GB at 4k context vs ~32GB usable → full. 19.0 GB needed of 32 GB usable — headroom for context
computed roofline: 897 GB/s × 0.46–0.76 efficiency window / 17.0GB (Q4_K_M) — bands, never points.
| model file | 17GB (GGUF Q4_K_M) |
| minimum memory | 22GB working set |
| this machine | 32GB HBM2, 897 GB/s |
| params | schnell fp8 |
| license | flux-dev-nc / apache schnell |
| price | $645 |
easy run: no stock runtime yet
→ ASUS ExpertCenter Pro ET900N G3 (GB300) — this model on the biggest machine
→ every model the Tesla V100 32GB (used) can run — full list
→ RTX 3090 (24GB, used) — upgrade path machine