local intelligence

can it run

Can the RTX 2080 / 2080 Super (8GB, used) run phi4 14B?

NO

No. 8GB of memory can't hold the 12GB working set this model needs. A smaller quant or a bigger machine is required.

~24–35 tok/s

weights 9.1GB + KV cache 0.78GB at 4k context vs ~8GB usable → offload-partial. 9.9 GB vs 8 GB usable — partial CPU offload, expect large speed loss

computed roofline: 448 GB/s × 0.48–0.72 efficiency window / 9.1GB (Q4_K_M) — bands, never points.

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

Specs

model file9.1GB (GGUF Q4_K_M)
minimum memory12GB working set
this machine8GB GDDR6, 448-496 GB/s
params14B
licensemit
price$305

Run it

model files: hugging face ↗

easy run: ollama pull phi4:14b

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

Alternatives

Tesla P40 (24GB, used) — cheapest machine that runs it ($290)

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

Buy

eBay (used) ↗ · Amazon ↗

2026-09-17 · ← all models on the RTX 2080 / 2080 Super (8GB, used) · ← full hardware catalog · prices verified at source, may drift