can it run
Comfortably. 8GB of memory against a 4GB working set leaves headroom for context, the OS, and anything else you're running.
weights 2GB + KV cache 0.44GB at 4k context vs ~8GB usable → full. 2.4 GB needed of 8 GB usable — headroom for context
computed roofline: 192.3 GB/s × 0.28–0.50 efficiency window / 2.0GB (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 | 2.0GB (GGUF Q4_K_M) |
| minimum memory | 4GB working set |
| this machine | 8GB GDDR5, 192 GB/s |
| params | 3B |
| license | llama3.2 (gated on HF) |
| price | $100 |
easy run: ollama pull llama3.2:3b
runs with: ollama · llama.cpp · koboldcpp · lm studio
→ every model the Tesla P4 (8GB, used) can run — full list
→ tesla-p100-16gb — the next step up from this machine's GPU