local intelligence

can it run

Can the Jetson Orin Nano Super dev kit run gemma3 12B?

NO

No. 8GB of memory can't hold the 11GB working set this model needs. A smaller quant or a bigger machine is required.

~2.1–5.5 tok/s

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.

explore the full catalog84 machines indexed · live prices · what each one can run

Specs

model file8.1GB (GGUF Q4_K_M)
minimum memory11GB working set
this machine8GB unified
params12B
licensegemma
price$499

Run it

model files: hugging face ↗

easy run: ollama pull gemma3:12b

runs with: ollama · llama.cpp · koboldcpp · lm studio

Alternatives

Tesla P100 (16GB, used) — cheapest machine that runs it ($135)

every model the Jetson Orin Nano Super dev kit can run — full list

Buy

NVIDIA (direct) ↗ · Amazon ↗

2026-09-17 · ← all models on the Jetson Orin Nano Super dev kit · ← full hardware catalog · prices verified at source, may drift