120B · MoE · 262,144 ctx · 2026-08-14

Nemotron 3 Super 120B

Runs on Data centre · Hugging Face ↗

vLLMllama.cpp

Coding index 37.7 (Artificial Analysis)

NVIDIA's 120B-total MoE (~12B active) — the best measured model in the 80 GB tier, tuned to run well on NVIDIA's own stack.

Sizes on disk

Real GGUF file sizes = weight VRAM. Add the KV cache for your context (≈3 GB at 32K, fp16).

~79 GB at Q4 — a single 80 GB card or a 2-GPU split. vLLM / TensorRT-LLM give the best throughput on NVIDIA hardware.