Skip to content

Text model · Nemotron

NE Can I run Llama-3.3-Nemotron-Super-49B-v1? Pick your device.

Llama-3.3-Nemotron-Super-49B-v1 is a 49B model. At Q4_K_M the weights are ~28.14 GB; with KV cache and runtime overhead, budget ~30.6 GB. Select your hardware below to see the full compatibility breakdown.

Memory figures are estimates. See methodology.