local intelligence

can it run

Can the CPU-only (DDR5 tuned / 4-channel) run llama3.1 8B?

FULL

5.4 GB needed of 30 GB usable — headroom for context

~30GB usable · CPU (DDR5) · model file 4.9GB · 8B

~16–26 tok/s

computed roofline: 179.2 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 (DDR5 tuned / 4-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 (DDR5 tuned / 4-channel) · fit = weights + 4k KV vs usable memory