can it run
No. 8GB of memory can't hold the 11GB working set this model needs. A smaller quant or a bigger machine is required.
weights 8.1GB + KV cache 1.5GB at 4k context vs ~6GB usable → no. 9.6 GB vs 6 GB usable — does not fit
computed roofline: 68 GB/s × 0.25–0.65 efficiency window / 8.1GB (Q4_K_M) — bands, never points.
| model file | 8.1GB (GGUF Q4_K_M) |
| minimum memory | 11GB working set |
| this machine | 8GB unified |
| params | 12B |
| license | gemma |
| price | $499 |
easy run: ollama pull gemma3:12b
runs with: ollama · llama.cpp · koboldcpp · lm studio
→ Tesla P100 (16GB, used) — cheapest machine that runs it ($135)
→ every model the Jetson Orin Nano Super dev kit can run — full list