Skip to content
Local AI Wizard
Your machine
Theme

Nemotron 3 family: which size to run

3 sizes, 30B–550B parameters · NVIDIA

Checked

Sizes

Nemotron 3 sizes
ModelArchitecture
Nemotron 3 Nano 30B A3BNVIDIA · NVIDIA Nemotron Open Model License · Dec 15, 202530BMoE · 3.5B active262,144No LiveBench result for this model in release 2026-06-2538*32*24.617.8
Nemotron 3 Super 120B A12BNVIDIA · NVIDIA Nemotron Open Model License · Mar 11, 2026120BMoE · 12B active262,144No LiveBench result for this model in release 2026-06-25989282.5†68
Nemotron 3 Ultra 550B A55BNVIDIA · OpenMDW 1.1 · Jun 4, 2026550BMoE · 55B active262,14467.4421*415*359.2†347

Each size is its own model, with its own scores and memory needs. Q4 estimates are planning figures, not measurements; file sizes are published. The Mac or PC column is for a 32 GB or larger machine (8 GB reserve); machines under 32 GB reserve 25% of their memory (2 to 8 GB), so they need less. The publisher lists Nano 30B-A3B, Super 120B-A12B, Ultra 550B-A55B. * The model's page explains why its estimate differs.

† Unsloth's dynamic UD-Q4_K_M file, shown when the repository has no plain Q4_K_M file (the same rule as the model pages); the cell's title names the file.

How to read this table

Q4 means compressed to about 4 bits per weight. GGUF (llama.cpp, Ollama, LM Studio) and MLX (Apple silicon) are file formats; the sizes shown are the published 4-bit files. A dash means no value is published or collected for that size; the reason is in the cell's accessible text.

Which size fits my machine

The largest size whose Q4 planning estimate fits what each machine offers. A planning estimate, not a measurement and not a speed. Smaller machines are left out; the largest one that fits no size is kept to show the limit.

Largest Nemotron 3 size per machine
MachineLargest Nemotron 3 size with enough memory
Mac mini M4 · 32 GB unified32No size of this family has a Q4 estimate within what this machine offersNo size fits, so there is no estimate to compare
Mac mini M5 Pro · 64 GB unified56Nemotron 3 Nano 30B A3B38
Mac Studio M5 Max · 128 GB unified104Nemotron 3 Super 120B A12B98
Mac Studio · M5 Ultra · 36-core CPU / 80-core GPU · 512 GB unified392Nemotron 3 Super 120B A12B98
RTX 4090 · 24 GB VRAM24No size of this family has a Q4 estimate within what this machine offersNo size fits, so there is no estimate to compare
RTX 5090 · 32 GB VRAM32Nemotron 3 Nano 30B A3B32
DGX H100 · 8 × 80 GB640Nemotron 3 Ultra 550B A55B429

A dash means no size of this family fits that machine. The requirement is the size's Q4 estimate with that machine's own reserve: a graphics card reserves 2 GB, as in the sizes table; a Mac or PC reserves 25% of its memory (2 to 8 GB), so below 32 GB its figure is lower than the sizes table's. A server profile reserves 2 GB per graphics card, so its figure is higher.

Smallest machine for each size

The profile with the least memory that still has enough for the size's Q4 estimate, from the hardware catalog.

Smallest machine per Nemotron 3 size
SizeSmallest Mac or PC-memory profileSmallest graphics-card profileServer-class profile
Nemotron 3 Nano 30B A3BMac mini 2024 · M4 Pro · 48 GBRTX 5090 · 32 GBDGX H100 · 8 × 80 GB · 640 GB
Nemotron 3 Super 120B A12BDGX Spark · 128 GBNo graphics-card profile in the catalog has enough memory for this sizeDGX H100 · 8 × 80 GB · 640 GB
Nemotron 3 Ultra 550B A55BNo Mac, laptop or PC profile in the catalog has enough memory for this sizeNo graphics-card profile in the catalog has enough memory for this sizeDGX H100 · 8 × 80 GB · 640 GB

A dash means no profile of that kind in the catalog has enough memory for the size.

Memory by file precision

The same planning formula at three precisions (0.625, 1.125 and 2 bytes per parameter, plus working room and the system reserve). Estimates, not measurements.

Nemotron 3 memory estimate by precision
Size
Nemotron 3 Nano 30B A3B38*32*49*43*80*74*
Nemotron 3 Super 120B A12B9892170164296290
Nemotron 3 Ultra 550B A55B421*415*751*745*1,328*1,322*

* The model's page explains why its estimate differs.

Family tree

Family, sizes and, for each size, the two 4-bit files the tables use (GGUF Q4_K_M and MLX 4-bit) when one was collected. Other precisions are not drawn here.

Nemotron 3 family: sizes and published filesSwipe sideways to see the files, or read the list below.
Nemotron 3 family: sizes and published filesFamilySizesFilesNemotron 3NVIDIANano 30B A3B3.5B activeGGUF Q4_K_M24.6 GBMLX 4-bit17.8 GBSuper 120B A12B12B activeGGUF UD-Q4_K_M82.5 GBMLX 4-bit68 GBUltra 550B A55B55B activeGGUF UD-Q4_K_M359.2 GBMLX 4-bit347 GB

The same tree as a list:

  • Nemotron 3 · NVIDIA
    • Nano 30B A3B · 3.5B active
      • GGUF Q4_K_M · 24.6 GB · unsloth/Nemotron-3-Nano-30B-A3B-GGUF, read Oct 23, 2026
      • MLX 4-bit · 17.8 GB · lmstudio-community/NVIDIA-Nemotron-3-Nano-30B-A3B-MLX-4bit, read Oct 17, 2026
    • Super 120B A12B · 12B active
      • GGUF UD-Q4_K_M · 82.5 GB · unsloth/NVIDIA-Nemotron-3-Super-120B-A12B-GGUF, read Oct 23, 2026
      • MLX 4-bit · 68 GB · mlx-community/NVIDIA-Nemotron-3-Super-120B-A12B-4bit, read Oct 23, 2026
    • Ultra 550B A55B · 55B active
      • GGUF UD-Q4_K_M · 359.2 GB · unsloth/NVIDIA-Nemotron-3-Ultra-550B-A55B-GGUF, read Oct 23, 2026
      • MLX 4-bit · 347 GB · mlx-community/Nemotron-3-Ultra-550B-A55B-4bit, read Oct 23, 2026

Learn more

Sources

Where the family and its sizes are named, and where each number comes from.