local intelligence

can it run

Can the CPU-only (DDR4-3200 dual-channel) run llama3.1 8B?

FULL

5.4 GB needed of 14 GB usable — headroom for context

~14GB usable · CPU (DDR4) · model file 4.9GB · 8B

~4.7–7.3 tok/s

computed roofline: 51.2 GB/s × 0.45–0.70 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)

every model the CPU-only (DDR4-3200 dual-channel) can run — full list

explore the full catalog84 machines indexed · live prices · what each one can run
2026-09-17 · ← all models on the CPU-only (DDR4-3200 dual-channel) · fit = weights + 4k KV vs usable memory