What is the minimum hardware to run Nemotron 3.5 Super VL 120B-A12B?

Apple M4 Max (128GB) is the lightest device that runs Nemotron 3.5 Super VL 120B-A12B, using ~87.4 GB at Q4_K_M of its ~96 GB usable. Anything with less usable memory cannot load it.

How much memory does Nemotron 3.5 Super VL 120B-A12B need?

At Q4_K_M it needs about 87.4 GB (weights ~83.96 GB + KV cache + overhead at 4k context). At Q8_0 budget ~130.9 GB.

Can I run Nemotron 3.5 Super VL 120B-A12B on a Mac?

Yes. Nemotron 3.5 Super VL 120B-A12B runs on Apple Silicon with enough unified memory; the ranked list below shows the lightest Mac that fits.

Can I run Nemotron 3.5 Super VL 120B-A12B on a phone?

No. Nemotron 3.5 Super VL 120B-A12B is too large for current phone memory at Q4_K_M; stick to a laptop, desktop GPU, or Mac.

Hardware guide · Nemotron

NE What hardware do you need to run Nemotron 3.5 Super VL 120B-A12B?

Nemotron 3.5 Super VL 120B-A12B needs about 87.4 GB to run at Q4_K_M, so the lightest hardware that runs it is Apple M4 Max (128GB). 5 of 49 devices tested can run it.

Needs (Q4_K_M): ~87.4 GB
Devices that run it: 5
Too small: 44
Lightest that runs it: ~96 GB

Recommended Q4_K_M

Nvidia DGX Spark (128GB) Yes

Runs at Q4_K_M using ~87.4 GB of ~112 GB usable.

What kind of hardware runs Nemotron 3.5 Super VL 120B-A12B

Of the 5 devices that run it, here is the split by hardware class.

2 discrete GPUs 3 Macs

Hardware that runs Nemotron 3.5 Super VL 120B-A12B

Ranked by usable memory, lightest first. Prices are approximate street prices for the device itself (a GPU is the card alone; a Mac is the whole machine). Tok/s is a bandwidth estimate; see methodology.

Compatible devices 5 total

Too small for Nemotron 3.5 Super VL 120B-A12B

See the full Nemotron 3.5 Super VL 120B-A12B memory breakdown, or compare it against other models.

Sources

huggingface.co · 2 sources
- huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16
- huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16/blob
ollama.com · 1 source
- ollama.com
registry.ollama.ai · 1 source
- registry.ollama.ai

Memory at Q4_K_M (87.4 GB = 83.96 GB weights + KV cache + overhead), Catalog updated 2026-11-01. See methodology.