Skip to content

Nemotron 3 Super 120B A12B on M3 Ultra 96 GB: VRAM, speed and fit

Nemotron 3 Super 120B A12B at 3-bit runs on the M3 Ultra 96 GB with 256K of context at about 42 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on M3 Ultra 96 GB · 3-bit (Q3_K_M) · Ollama / LM Studio · Chat

GPU memory
83.0 GB
of 96.0 GB
Context
256K
auto
Speed
42 tok/s
Very fast
First reply
7.5 s
2K prompt

Where the memory goes

Model
56.3 GB
Context
2.2 GB
Overhead
640 MB
OS
24.0 GB
Free
13.0 GB
Memory
83.0 GB of 96.0 GB
Context
256K tokens · auto
Speed
42 tok/s · very fast
First reply
7.5 s for a 2K prompt
Running cost
$3.55/mo at home · $117/mo on a cloud 4× RTX 2000 Ada

Validation: Not validated

What Nemotron 3 Super 120B A12B on M3 Ultra 96 GB was checked against
CheckTargetResultStatus
Fits in GPU memory72.0 GB usable59.0 GB neededPass
Headroom5% free13.0 GB free (18%)Pass
Context for chat16K or more256KPass
Writing speed15 tok/s or more42 tok/sPass
First replyunder 3 s, 2K prompt7.5 sFails

Targets: a reply you can read along with, a first reply the use case tolerates, and 5% of memory left free. Calculated from published specs, not benchmarked.

The setup

Model
Nemotron 3 Super 120B A12B
Parameters
124B, 12B active
Precision
3-bit (Q3_K_M)
Context
256K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
M3 Ultra 96 GB
GPU can use
72.0 GB of 96.0 GB

Running cost

At home
$3.55/mo
162 W at the wall
Renting instead
$117/mo
4× RTX 2000 Ada at $0.96/h

4 h a day, power at $0.18 per kWh, cloud at RunPod on-demand prices as of Nov 22, 2026.

How to run it

Ollama
ollama run nemotron-3-super:120b-a12b
llama.cpp
llama-server -hf unsloth/NVIDIA-Nemotron-3-Super-120B-A12B-GGUF
vLLM
vllm serve nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16
MLX (Mac)
mlx_lm.chat --model mlx-community/NVIDIA-Nemotron-3-Super-120B-A12B-4bit

Nemotron 3 Super 120B A12B on similar machines

All machines: Nemotron 3 Super 120B A12B VRAM requirements. Everything that runs here: what can the M3 Ultra 96 GB run?

Other models that run on M3 Ultra 96 GB

Questions

Can Nemotron 3 Super 120B A12B run on M3 Ultra 96 GB?

Nemotron 3 Super 120B A12B at 3-bit runs on the M3 Ultra 96 GB with 256K of context at about 42 tokens a second.

Report VR-0IAUFZ4, calculated Nov 22, 2026 from published specs, not benchmarked.