local intelligence

can it run

Can the Tesla M60 (16GB, used) run mistral-nemo 12B?

YES

Comfortably. 16GB of memory against a 9GB working set leaves headroom for context, the OS, and anything else you're running.

~6.3–11 tok/s

weights 7.1GB + KV cache 0.62GB at 4k context vs ~16GB usable → full. 7.7 GB needed of 16 GB usable — headroom for context

computed roofline: 160.4 GB/s × 0.28–0.50 efficiency window / 7.1GB (Q4_K_M) — bands, never points.

explore the full catalog90 machines indexed · live prices · what each one can run

Specs

model file7.1GB (GGUF Q4_K_M)
minimum memory9GB working set
this machine16GB GDDR5 (2×8 GB), 160 GB/s
params12B
licenseapache-2.0
price$35

Run it

model files: hugging face ↗

easy run: ollama pull mistral-nemo:12b

runs with: ollama · llama.cpp · koboldcpp · lm studio

Alternatives

every model the Tesla M60 (16GB, used) can run — full list

tesla-p100-16gb — the next step up from this machine's GPU

Buy

eBay (used) ↗ · Amazon ↗

2026-09-20 · ← all models on the Tesla M60 (16GB, used) · ← full hardware catalog · prices verified at source, may drift