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: 936 GB/s × 0.46–0.76 efficiency window / 17.0GB (Q4_K_M) — bands, never points.
Community check: ~26 tok/s · 20-27B Q4 · 20 runs · inside our computed band — localmaxxing.com
→explore the full catalog84 machines indexed · live prices · what each one can run| model file | 17GB (GGUF Q4_K_M) |
| minimum memory | 22GB working set |
| this machine | 24GB GDDR6X, 936 GB/s |
| params | 27B |
| license | gemma |
| price | $1100 |
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
→ rtx-5090 — the next step up from this machine's GPU
NVIDIA (used market) ↗ · Amazon ↗