Skip to content
localmodel.run

Text model · Nemotron

NE Nemotron 3.5 Super VL 120B-A12B: RAM and VRAM requirements

Nemotron 3.5 Super VL 120B-A12B needs about 87.4 GB to run at Q4_K_M (the Q4_K_M GGUF file is ~83.96 GB to download; KV cache and overhead add the rest), or about 130.9 GB at Q8_0. The lightest hardware that runs it is Apple M4 Max (128GB).

Nemotron family · 120B params (Mixture-of-Experts: activates only 12B of 120B params per token, so generation is faster than the total size suggests) · released Oct 2026.

Shopping for hardware? See what runs Nemotron 3.5 Super VL 120B-A12B →

Vision · accepts images License OpenMDW-1.1 · Commercial OK ↓ 56.3K/mo ♥ 110 on HuggingFace
Q4_K_M GGUF
83.96 GB
Q8_0 GGUF
-
Memory @ Q4 (4k)
~87.4 GB
Context
1024 k

Q4_K_M and Q8_0 are GGUF download (file) sizes. Memory @ Q4 includes the KV cache and overhead, so it runs larger than the file on disk.

Will it run on your device?

Nemotron 3.5 Super VL 120B-A12B runs on 5 of 49 tracked devices at Q4_K_M.

2 run well 3 tight fit 44 too small
Fit check Q4_K_M
No, not enough memory
needs 87.4 GB usable 10.5 GB
See the full breakdown

Memory breakdown

Weights (Q4_K_M)83.96 GB
+
KV cache (4k)2.6 GB
+
Overhead0.8 GB
=
Total87.4 GB

How context length changes it

4k context ~87.4 GB 32k context ~105.8 GB 128k context ~168.9 GB

Longer context grows the KV cache, which for Nemotron 3.5 Super VL 120B-A12B is sized by its 12B active params, not the full 120B. It needs ~87.4 GB at 4k and ~168.9 GB at 128k.

Quantization sizes

GGUF quantson disk
Quantization Size on disk
Q2_K 50.3 GB est
Q3_K_M 58.7 GB est
Q4_K_M (default) 83.96 GB
Q5_K_M 85.5 GB est
Q6_K 98.4 GB est
Q8_0 127.5 GB est
FP16 240 GB est

Lower quant = smaller and faster, slightly lower quality. Q4_K_M is the common default.

Run it

Ollama
$ ollama run nemotron-3.5-super:120b-a12b-q4_K_M

Which devices can run Nemotron 3.5 Super VL 120B-A12B?

NVIDIA GPUs

Apple Silicon Macs

RAM-only laptops

iPhone & iPad

Android

AMD GPUs

Same job, different size

Pick by what fits your memory: step down to free up VRAM, or step up if you have headroom.

Next size down Laguna S 2.1 118B Next size up Devstral 2 123B 123B

Similar models

Head-to-head

FAQ

How much VRAM or RAM does Nemotron 3.5 Super VL 120B-A12B need?

At Q4_K_M, Nemotron 3.5 Super VL 120B-A12B needs about 87.4 GB (weights ~83.96 GB + KV cache + overhead) at a 4k context. At Q8_0 budget ~130.9 GB.

What is the Q4_K_M GGUF file size of Nemotron 3.5 Super VL 120B-A12B?

The Q4_K_M GGUF file is about 83.96 GB to download, and the Q8_0 GGUF is about 127.5 GB. That is the weights file on disk; to run it you also need room for the KV cache and overhead, so budget ~87.4 GB of memory at Q4_K_M.

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

Nemotron 3.5 Super VL 120B-A12B is large; you need a high-memory Mac or multi-GPU setup at Q4_K_M.

Is Nemotron 3.5 Super VL 120B-A12B cheaper to run because it is a MoE model?

It is faster, not lighter. Nemotron 3.5 Super VL 120B-A12B activates only 12B of 120B params per token (so it runs quickly), but all experts must stay in memory, so it still needs memory for the full 120B.

Can I use Nemotron 3.5 Super VL 120B-A12B commercially?

Yes. Nemotron 3.5 Super VL 120B-A12B is licensed OpenMDW-1.1, which permits commercial use.

Understand the numbers

Short guides to the ideas behind Nemotron 3.5 Super VL 120B-A12B's memory and quant figures.

Vision-language Mamba/Transformer MoE: 120B total and 12B active, vendor context 1,048,576 tokens. Q4_K_M uses the exact Ollama model layer (88,419,818,592 bytes) plus the vision projector (1,733,696,896 bytes), converted to GiB. This combined footprint matches the install command. Context memory remains the calculator estimate.

Sources

Catalog updated 2026-11-01. Memory figures are estimates. See methodology.