local intelligence

can it run

Can the RTX 4090 (24GB, used) run llama3.2 1B?

YES

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

~360–590 tok/s

weights 1.3GB + KV cache 0.12GB at 4k context vs ~24GB usable → full. 1.4 GB needed of 24 GB usable — headroom for context

computed roofline: 1008 GB/s × 0.46–0.76 efficiency window / 1.3GB (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 file1.3GB (GGUF Q4_K_M)
minimum memory4GB working set
this machine24GB GDDR6X
params1B
licensellama3.2 (gated on HF)
price$2000

Run it

model files: hugging face ↗

easy run: ollama pull llama3.2:1b

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

Alternatives

no alternatives — every machine in the catalog can run this one.

rtx-5090 — the next step up from this machine's GPU

Buy

eBay (used) ↗ · Amazon (new) ↗

2026-09-17 · ← full hardware catalog · prices verified at source, may drift