Skip to main content
Watch: I Built an AI App Without Leaving Databricks

NVIDIA - Mixture of experts - verified

Run NVIDIA Nemotron 3.5 Super VL 120B-A12B locally

NVIDIA Nemotron 3.5 Super VL 120B-A12B is a 124.5B mixture-of-experts (12B active) model from NVIDIA with a 1.05M-token context window, released under OpenMDW License 1.1 (commercial use is allowed); the smallest listed download is 71.8 GB, the Q4_0 GGUF build from ggml-org/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-GGUF.

Official weights: nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 - modalities: text, image, video

Total params
124.5B
Active params
12B
Context
1.05M
Smallest download
71.8 GB

Fits in

Smallest download at most 85% of memory

Downloads

The official weights and every quantization listed for this model, with file sizes from Hugging Face.

NVIDIA Nemotron 3.5 Super VL 120B-A12B downloads and file sizes
DownloadFormatSizeRepo
Official weightsBF16248.9 GBnvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16
Q4_0Smallest listedGGUF71.8 GBggml-org/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-GGUF
Q8_0GGUF128.5 GBggml-org/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-GGUF

GB is decimal: 1 GB = 10^9 bytes. Add memory for the context and the operating system on top of the file size.

Run it

Copied verbatim from the page linked under each command. Server commands from model cards often assume a multi-GPU node; check the flags before you run them.

Ollama

Terminal
ollama run nemotron-3.5-super

Source: ollama.com/library/nemotron-3.5-super

vLLM

Terminal
vllm serve $MODEL \
  --served-model-name nemotron-3.5-super-vl \
  --tensor-parallel-size 4 \
  --trust-remote-code \
  --gpu-memory-utilization=0.85 \
  --allowed-local-media-path=/ \
  --max-num-seqs=32 \
  --limit-mm-per-prompt '{"video": 1, "image": 1}' \
  --video-pruning-rate 0.5 \
  --media-io-kwargs '{"video": {"fps": 2, "num_frames": 256}}' \
  --enable-auto-tool-choice \
  --tool-call-parser qwen3_coder \
  --reasoning-parser nemotron_v3 \
  --speculative_config.method mtp \
  --speculative_config.num_speculative_tokens 3

Source: huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16

Not sure which runtime to use? Compare local LLM runtimes by platform, API and features.

License

Commercial use
Commercial use: YesCommercial use is allowed.
Gated download
No. The files download directly.

Worth knowing

The card's BF16 vLLM recipe targets 4x H100 (or 2x GB200) and expects MODEL exported as the repo id first.

Released (per the model card).

FAQ

How big is the NVIDIA Nemotron 3.5 Super VL 120B-A12B download?

The official BF16 weights in nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 are 248.9 GB. The smallest listed download is 71.8 GB, the Q4_0 GGUF build from ggml-org/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-GGUF. Plan for more memory than the file size: the context (KV cache) and the operating system need room too.

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

NVIDIA Nemotron 3.5 Super VL 120B-A12B is released under OpenMDW License 1.1, and commercial use is allowed. The license text is at https://openmdw.ai/license/1-1/.

How much memory do I need for NVIDIA Nemotron 3.5 Super VL 120B-A12B?

By this directory's rule of thumb it fits in 128 GB and up: the smallest listed download, 71.8 GB, is at most 85% of 128 GB, which leaves room for the context and the operating system.

How do I run NVIDIA Nemotron 3.5 Super VL 120B-A12B with Ollama?

Run "ollama run nemotron-3.5-super", as shown at https://ollama.com/library/nemotron-3.5-super. The Ollama library lists the nemotron-3.5-super:120b tag at 80GB - 90GB.

What is the context length of NVIDIA Nemotron 3.5 Super VL 120B-A12B?

1,048,576 tokens. A longer context needs more memory for the KV cache, so you can run with a shorter one when memory is tight.

Sources

Last verified from the pages below.

Newsletter

New open weights, every week

One email per week. New model releases, open-weight drops and what they mean for what you build.

Keep exploring

Best local AI models

Our curated picks by hardware tier, with benchmarks and the reasoning.

Model API pricing and specs

First-party prices per 1M tokens when you would rather call an API.

AI benchmark leaderboards

Sourced scores, for when you need to compare quality.

Setup guides

Point your coding tools at the model you picked.