local intelligence

can it run

Can the Titan RTX (24GB, used) run llama3.2 3B?

YES

Comfortably. 24GB of memory against a 4GB working set leaves headroom for context, the OS, and anything else you're running.

~160–240 tok/s

weights 2GB + KV cache 0.44GB at 4k context vs ~24GB usable → full. 2.4 GB needed of 24 GB usable — headroom for context

computed roofline: 672 GB/s × 0.48–0.72 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).

explore the full catalog84 machines indexed · live prices · what each one can run

Specs

model file2.0GB (GGUF Q4_K_M)
minimum memory4GB working set
this machine24GB GDDR6, 672 GB/s
params3B
licensellama3.2 (gated on HF)
price$900

Run it

model files: hugging face ↗

easy run: ollama pull llama3.2:3b

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

Alternatives

every model the Titan RTX (24GB, used) can run — full list

rtx-3090 — the next step up from this machine's GPU

Buy

eBay (used) ↗ · Amazon ↗

2026-09-17 · ← all models on the Titan RTX (24GB, used) · ← full hardware catalog · prices verified at source, may drift