local intelligence

can it run

Can the NVIDIA RTX A2000 12GB run qwen3 8B?

FULL

5.8 GB needed of 12 GB usable — headroom for context

12GB · Ampere · model file 5.2GB · 8B

~30–49 tok/s

computed roofline: 288 GB/s × 0.55–0.88 efficiency window / 5.2GB (Q4_K_M) — bands, never points.

Run qwen3 8B on instead

Tesla P100 (16GB, used) — cheapest catalog machine that runs qwen3 8B fully ($135)

rtx-a4000 — the next step up from NVIDIA RTX A2000 12GB

every model the NVIDIA RTX A2000 12GB 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 RTX A2000 12GB · fit = weights + 4k KV vs usable memory