can it run
Comfortably. 72GB of memory against a 28GB working set leaves headroom for context, the OS, and anything else you're running.
| model file | 22GB (GGUF Q4_K_M) |
| minimum memory | 28GB working set |
| this machine | 72GB GDDR7, ~1.3 TB/s |
| params | 32B |
| license | apache-2.0 |
| price | $9210 |
easy run: ollama pull qwen2.5vl:32b
runs with: ollama · llama.cpp · koboldcpp · lm studio
→ ASUS ExpertCenter Pro ET900N G3 (GB300) — this model on the biggest machine