NVIDIA · 120B · MoE

Can you run Nemotron 3 Super 120B-A12B locally?

Nemotron 3 Super 120B-A12B is a mixture-of-experts model with 120B parameters, 12B active per token. At 4-bit or better it runs on 26 of the 120 hardware configurations listed here; the smallest is the RTX PRO 6000 Blackwell (96 GB). On a 128 GB DGX Spark it runs at Q4_K_M, at roughly 23 tokens per second (reported).

Data as of 2 November 2026

Fastest machines for Nemotron 3 Super 120B-A12B

Every machine that runs it, fastest first. Filter by type; your machine is marked. Compare machines running it side by side

1RTX PRO 6000 BlackwellGraphics card · 96 GB~114 tok/s our est.Q4_K_M · 90 of 95 GB
22x RTX PRO 6000 BlackwellGraphics card · 192 GB~95 tok/s ModelFit est.Q4_K_M · 90 of 190 GB
3M3 UltraMac · 96 GB · 2 variants~70 tok/s our est.IQ4_XS · 67 GB
4M2 Ultra · 96 GBMac · 96 GB~68 tok/s our est.IQ4_XS · 67 of 72 GB
5M5 UltraMac · 256–512 GB · 3 variants~61 tok/s ModelFit est.Q4_K_M · 90 GB
6M3 UltraMac · 256–512 GB · 3 variants~41 tok/s ModelFit est.Q4_K_M · 90 GB
7M2 UltraMac · 128–192 GB · 4 variants~37 tok/s ModelFit est.Q4_K_M · 90 GB
8M2 Max · 96 GB · 38cMac · 96 GB~34 tok/s our est.IQ4_XS · 67 of 72 GB
9M1 UltraMac · 128 GB · 2 variants~34 tok/s ModelFit est.Q4_K_M · 90 GB
10M5 Max · 128 GB · 40cMac · 128 GB~33 tok/s ModelFit est.Q4_K_M · 90 of 96 GB
11M4 Max · 128 GB · 40cMac · 128 GB~28 tok/s ModelFit est.Q4_K_M · 90 of 96 GB
12M3 Max · 96 GB · 30cMac · 96 GB~26 tok/s our est.IQ4_XS · 67 of 72 GB
13DGX Spark (GB10)AI mini PC · 128 GB~23 tok/s reportedQ4_K_M · 90 of 122 GB
14M3 Max · 128 GB · 40cMac · 128 GB~22 tok/s ModelFit est.Q4_K_M · 90 of 96 GB
15Ryzen AI Max+ 395 · 128 GBAI mini PC · 128 GB~13 tok/s ModelFit est.Q4_K_M · 90 of 96 GB
16M5 UltraMac · 96 GB · 2 variantsno estimateIQ4_XS · 67 GB

Too big for 94 machines

2x RTX 5090, Ryzen AI Max+ 395 · 64 GB, M2 Ultra · 64 GB · 76c, M2 Ultra · 64 GB · 60c, M1 Ultra · 64 GB · 64c, M1 Ultra · 64 GB · 48c, M5 Max · 64 GB · 40c, M4 Max · 64 GB · 40c, M3 Max · 64 GB · 40c, M2 Max · 64 GB · 38c, M2 Max · 64 GB · 30c, M1 Max · 64 GB · 32c, M1 Max · 64 GB · 24c, M5 Pro · 64 GB · 20c, M5 Pro · 64 GB · 16c, M4 Pro · 64 GB · 20c, M4 Pro · 64 GB · 16c, 2x RTX 4090, 2x RTX 3090 Ti, 2x RTX 3090, 2x RX 7900 XTX, M5 Max · 48 GB · 40c, M4 Max · 48 GB · 40c, M3 Max · 48 GB · 40c, M5 Pro · 48 GB · 20c, M5 Pro · 48 GB · 16c, M4 Pro · 48 GB · 20c, M4 Pro · 48 GB · 16c, RTX 5090, M5 Max · 36 GB · 32c, M4 Max · 36 GB · 32c, M3 Max · 36 GB · 30c, M3 Pro · 36 GB, RTX 4090, RTX 3090 Ti, RTX 3090, RX 7900 XTX, M2 Max · 32 GB · 38c, M2 Max · 32 GB · 30c, M1 Max · 32 GB · 32c, M1 Max · 32 GB · 24c, M2 Pro · 32 GB, M1 Pro · 32 GB, M6 · 32 GB · 12c, M5 · 32 GB · 10c, M5 · 32 GB · 8c, M4 · 32 GB, RX 7900 XT, M5 Pro · 24 GB · 20c, M5 Pro · 24 GB · 16c, M4 Pro · 24 GB · 20c, M4 Pro · 24 GB · 16c, M6 · 24 GB · 12c, M6 · 24 GB · 10c, M5 · 24 GB · 10c, M5 · 24 GB · 8c, M4 · 24 GB, M3 · 24 GB, M2 · 24 GB, RTX 5080, RTX 5070 Ti, RTX 5060 Ti, RTX 4080 SUPER, RTX 4080, RTX 4070 Ti SUPER, RTX 4060 Ti, Tesla T4, Tesla P100, RX 9070 XT, RX 9060 XT, M3 Pro · 18 GB, RTX 5070, RTX 4070 Ti, RTX 4070 SUPER, RTX 4070, RTX 3060, M2 Pro · 16 GB, M1 Pro · 16 GB, M6 · 16 GB · 12c, M6 · 16 GB · 10c, M5 · 16 GB · 10c, M5 · 16 GB · 8c, M4 · 16 GB, M3 · 16 GB, M2 · 16 GB, M1 · 16 GB, RTX 5060, RTX 4060, RTX 3070, RTX 3060 Ti, RTX 2070, M3 · 8 GB, M2 · 8 GB, M1 · 8 GB. Nemotron 3 Super 120B-A12B needs about 67 GB at its smallest build.

Speeds are single-user decode estimates, not measurements. "ModelFit est." comes from ModelFit's model fitted on published runs (CC BY 4.0); "our est." is memory bandwidth divided by bytes read per token, times 0.55. Memory is what the best build needs, against what the machine can give a model. Method

DGX Spark, reported

22.7 to 23.7 tok/s

NVFP4 under stock vLLM, single user, per the vLLM project. Source and setup in the GPUwerk guide

About the model

Parameters: 120B
Active per token: 12B
Type: Mixture of experts
Good for: Large MoE for agents and RAG
Model card: Hugging Face

Builds and how to run them

Quantization	Load	Min. RAM	Command
Q4_K_M	87 GB	128 GB	`ollama run nemotron-3-super:120b`
IQ4_XS	64 GB	96 GB	GGUF or MLX build

Load, minimum RAM and Ollama commands: ModelFit, CC BY 4.0. Load is memory with the model loaded, before long contexts.

Questions

Can I run Nemotron 3 Super 120B-A12B on a Mac?

Yes on a Mac with enough memory: the smallest Apple configuration listed here that runs it at 4-bit or better is the M5 Ultra · 96 GB · 80c.

How much memory does Nemotron 3 Super 120B-A12B need?

About 67 GB at the smallest build in our data, including a margin for the runtime and an 8K-token context. Longer contexts need more.

Does Nemotron 3 Super 120B-A12B run on a DGX Spark?

Yes, at Q4_K_M. The Spark has 128 GB of unified memory, about 121.6 GB usable.