Skip to content

Head-to-head · Nemotron 3

Nemotron 3 Nano 4B vs Nemotron 3 Super 120B-A12B

Nemotron 3 Nano 4B needs ~3.9 GB at Q4_K_M; Nemotron 3 Super 120B-A12B needs ~80.3 GB. That ~76.4 GB gap decides which hardware runs each; they differ on 12 of the 14 devices below.

Spec Nemotron 3 Nano 4B Nemotron 3 Super 120B-A12B
Parameters4B120B MoE
Memory at Q4_K_M~3.9 GB~80.3 GB
Context window256k256k
LMArenanot rankednot ranked
Licensenvidia-nemotron-open-model-licensenvidia-nemotron-open-model-license

Which devices run each

A representative spread across the memory range. Tap a verdict for the full breakdown.

Size at each quantization

Quant Nemotron 3 Nano 4B Nemotron 3 Super 120B-A12B
Q2_K 1.7 GB* 50.3 GB*
Q3_K_M 2 GB* 58.7 GB*
Q4_K_M 2.64 GB 76.87 GB
Q5_K_M 2.9 GB* 85.5 GB*
Q6_K 3.3 GB* 98.4 GB*
Q8_0 3.94 GB 119.65 GB
FP16 7.41 GB 224.93 GB

* derived from bits-per-weight; unstarred sizes are measured GGUF files.

Bottom line

The larger Nemotron 3 Super 120B-A12B needs ~80.3 GB; Nemotron 3 Nano 4B runs on lighter hardware at ~3.9 GB with more headroom and faster responses. Check each against your exact device: what runs Nemotron 3 Nano 4B · what runs Nemotron 3 Super 120B-A12B.

More Nemotron 3 comparisons

FAQ

What is the difference in memory between Nemotron 3 Nano 4B and Nemotron 3 Super 120B-A12B?

At Q4_K_M, Nemotron 3 Nano 4B needs about 3.9 GB and Nemotron 3 Super 120B-A12B needs about 80.3 GB, a difference of ~76.4 GB.

Should I run Nemotron 3 Nano 4B or Nemotron 3 Super 120B-A12B?

Run Nemotron 3 Super 120B-A12B if your hardware has the ~80.3 GB it needs and you want maximum quality; run Nemotron 3 Nano 4B (~3.9 GB) for lighter hardware, faster responses, and more memory headroom.

Full breakdowns: Nemotron 3 Nano 4B · Nemotron 3 Super 120B-A12B · all models × devices.

Sources

Memory figures are estimates at Q4_K_M, validated 2026-08-03. See methodology.