can it run
Yes, but close to the edge. 24GB against a 22GB working set: it runs, with little room for long context windows or other processes.
weights 17GB + KV cache 1.94GB at 4k context vs ~24GB usable → full. 18.9 GB needed of 24 GB usable — headroom for context
computed roofline: 672 GB/s × 0.48–0.72 efficiency window / 17.0GB (Q4_K_M) — bands, never points.
| model file | 17GB (GGUF Q4_K_M) |
| minimum memory | 22GB working set |
| this machine | 24GB GDDR6, 672 GB/s |
| params | 27B |
| license | gemma |
| price | $900 |
easy run: ollama pull gemma3:27b
runs with: ollama · llama.cpp · koboldcpp · lm studio
→ Mac mini M4 (32GB) — cheapest machine that runs it ($999)
→ ASUS ExpertCenter Pro ET900N G3 (GB300) — this model on the biggest machine
→ every model the Titan RTX (24GB, used) can run — full list
→ rtx-3090 — the next step up from this machine's GPU