can it run
No. 8GB of memory can't hold the 54GB working set this model needs. A smaller quant or a bigger machine is required.
weights 43GB + KV cache 1.25GB at 4k context vs ~6GB usable → no. 44.2 GB vs 6 GB usable — does not fit
computed roofline: 68 GB/s × 0.25–0.65 efficiency window / 43.0GB (Q4_K_M) — bands, never points.
| model file | 43GB (GGUF Q4_K_M) |
| minimum memory | 54GB working set |
| this machine | 8GB unified |
| params | 70B |
| license | llama3.3 (gated on HF) |
| price | $499 |
easy run: ollama pull llama3.3:70b
runs with: ollama · llama.cpp · koboldcpp · lm studio
→ NIMO AI Mini PC (128GB) — cheapest machine that runs it ($1999)
→ every model the Jetson Orin Nano Super dev kit can run — full list