can it run
Yes, but close to the edge. 8GB against a 6GB working set: it runs, with little room for long context windows or other processes.
weights 4.7GB + KV cache 2GB at 4k context vs ~8GB usable → tight. 6.7 of 8 GB usable — keep context modest
computed roofline: 448 GB/s × 0.48–0.72 efficiency window / 4.7GB (Q4_K_M) — bands, never points.
Community check: ~52 tok/s · 8-9B Q4 · 4 runs · inside our computed band — localmaxxing.com
→explore the full catalog84 machines indexed · live prices · what each one can run| model file | 4.7GB (GGUF Q4_K_M) |
| minimum memory | 6GB working set |
| this machine | 8GB GDDR6, 448-496 GB/s |
| params | 7B |
| license | apache-2.0 |
| price | $305 |
easy run: ollama pull llava:7b
runs with: ollama · llama.cpp · koboldcpp · lm studio
→ Tesla P100 (16GB, used) — cheapest machine that runs it ($135)
→ every model the RTX 2080 / 2080 Super (8GB, used) can run — full list
→ rtx-3080-10gb — the next step up from this machine's GPU