can it run
Comfortably. 16GB of memory against a 4GB working set leaves headroom for context, the OS, and anything else you're running.
weights 1.3GB + KV cache 0.12GB at 4k context vs ~16GB usable → full. 1.4 GB needed of 16 GB usable — headroom for context
computed roofline: 900 GB/s × 0.46–0.76 efficiency window / 1.3GB (Q4_K_M) — bands, never points. Small models (under ~4.5B) run BELOW these bands — kernel-launch overhead keeps them from saturating bandwidth (measured against community medians, 09-06).
| model file | 1.3GB (GGUF Q4_K_M) |
| minimum memory | 4GB working set |
| this machine | 16GB HBM2, 900 GB/s |
| params | 1B |
| license | llama3.2 (gated on HF) |
| price | $340 |
easy run: ollama pull llama3.2:1b
runs with: ollama · llama.cpp · koboldcpp · lm studio
→ every model the Tesla V100 (16GB, used) can run — full list
→ RTX 3090 (24GB, used) — upgrade path machine