can it run
21.0 of 20 GB usable — barely over; real with q8 KV cache (halves KV) or shorter context
20GB · Ampere · model file 20GB · distill 32B
computed roofline: 640 GB/s × 0.46–0.76 efficiency window / 20.0GB (Q4_K_M) — bands, never points.
→ Mac mini M4 (32GB) — cheapest catalog machine that runs DEEPSEEK-R1 distill 32B fully ($999)
→ rtx-a5000 — the next step up from NVIDIA RTX A4500
→ every model the NVIDIA RTX A4500 can run — full list
→explore the full catalog84 machines indexed · live prices · what each one can run