can it run
Only with compromises. 16GB is below the 19GB working set — expect a lower quant, offloading, or heavy swap. Possible, not pleasant.
weights 14.6GB + KV cache 0.62GB at 4k context vs ~16GB usable → tight. 15.2 of 16 GB usable — keep context modest
computed roofline: 732 GB/s × 0.17–0.38 efficiency window / 14.6GB (Q4_K_M) — bands, never points.
| model file | 14.6GB (GGUF Q4_K_M) |
| minimum memory | 19GB working set |
| this machine | 16GB HBM2, 732 GB/s |
| params | 24B |
| license | apache-2.0 |
| price | $135 |
easy run: ollama pull devstral:24b
runs with: ollama · llama.cpp · koboldcpp · lm studio
→ Mac mini M4 (32GB) — cheapest machine that runs it ($999)
→ ASUS ExpertCenter Pro ET900N G3 (GB300) — this model on the biggest machine
→ every model the Tesla P100 (16GB, used) can run — full list
→ tesla-v100-16gb — the next step up from this machine's GPU