local intelligence

can it run

Can the Intel Arc Pro B70 (Battlemage Pro) run llama3.2 3B?

FULL

2.4 GB needed of 32 GB usable — headroom for context

32GB · Battlemage · model file 2.0GB · 3B

~180–240 tok/s

computed roofline: 608 GB/s × 0.60–0.78 efficiency window / 2.0GB (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).

Community check: ~97 tok/s · 3-4B Q4 · 3 runs · below our band — expected for small models (kernel-launch overhead) — localmaxxing.com

Run llama3.2 3B on instead

Raspberry Pi 5 + AI Kit (Hailo-8L) — cheapest catalog machine that runs llama3.2 3B fully ($110)

rtx-3090 — the next step up from Intel Arc Pro B70 (Battlemage Pro)

every model the Intel Arc Pro B70 (Battlemage Pro) can run — full list

explore the full catalog84 machines indexed · live prices · what each one can run
2026-09-17 · ← all models on the Intel Arc Pro B70 (Battlemage Pro) · fit = weights + 4k KV vs usable memory