local intelligence

can it run

Can the NVIDIA GeForce RTX 4080 run llama3.1 8B?

FULL

5.4 GB needed of 16 GB usable — headroom for context

16GB · Ada · model file 4.9GB · 8B

~67–110 tok/s

computed roofline: 716.8 GB/s × 0.46–0.76 efficiency window / 4.9GB (Q4_K_M) — bands, never points.

Run llama3.1 8B on instead

Tesla P100 (16GB, used) — cheapest catalog machine that runs llama3.1 8B fully ($135)

rtx-4090 — the next step up from NVIDIA GeForce RTX 4080

every model the NVIDIA GeForce RTX 4080 can run — full list

explore the full catalog84 machines indexed · live prices · what each one can run
2026-09-17 · ← all models on the NVIDIA GeForce RTX 4080 · fit = weights + 4k KV vs usable memory