News — NVIDIA A40
What Can You Actually Run on a 48GB NVIDIA A40? Measured Model Sizes and Tokens Per Second (2026)
One A40 48GB runs 27–34B models at 23–29 tokens/sec, fits a 70B at Q4 at 12–13.5 tokens/sec, and serves 1,705 tokens/sec of aggregate output on an 8B model at 100 concurrent requests. The measured numbers, the KV cache math behind the 72B cliff, and the three things an Ampere card cannot do.
Putting an NVIDIA A40 in a PowerEdge R740xd: Every Part Dell Doesn't Tell You You Need
An NVIDIA A40 48GB works in a Dell PowerEdge R740xd — but the card is not the purchase. The full bill of materials: GPU enablement kit 330-BBMO (US) / 490-BEIX (EMEA), low-profile heat sinks in both CPU sockets, the high-performance fan kit, air shroud and mylar, a dedicated GPU power cable, and PSUs of 1100W or higher — plus the two mistakes that quietly ruin most self-assembled builds.