can it run
Yes, but close to the edge. 64GB against a 54GB working set: it runs, with little room for long context windows or other processes.
weights 43GB + KV cache 1.25GB at 4k context vs ~62GB usable → full. 44.2 GB needed of 62 GB usable — headroom for context
computed roofline: 273 GB/s × 0.55–0.80 efficiency window / 43.0GB (Q4_K_M) — bands, never points.
| model file | 43GB (GGUF Q4_K_M) |
| minimum memory | 54GB working set |
| this machine | 64GB unified |
| params | distill 70B |
| license | mit |
| price | $2199 |
easy run: ollama pull deepseek-r1:70b
runs with: ollama · llama.cpp · koboldcpp · lm studio
→ NIMO AI Mini PC (128GB) — cheapest machine that runs it ($1999)
→ ASUS ExpertCenter Pro ET900N G3 (GB300) — this model on the biggest machine