can it run
25.0 of 24 GB usable — barely over; real with q8 KV cache (halves KV) or shorter context
24GB · Ampere GA102 · model file 23GB · dev fp8
computed roofline: 936 GB/s × 0.46–0.76 efficiency window / 23.0GB (Q4_K_M) — bands, never points.
→ Mac mini M5 Pro (64GB) — cheapest catalog machine that runs FLUX dev fp8 fully ($1669)
→ rtx-5090 — the next step up from NVIDIA RTX 3090
→ every model the NVIDIA RTX 3090 can run — full list
→explore the full catalog84 machines indexed · live prices · what each one can run