NE

NVIDIA Nemotron 3.5 Super VL 120B A12B

NemotronGGUF by natalie5Updated 2026-10-15
Download on Hugging Face
Parameters1.63B
Context1024K
Layers5
Architecturedflash
Smallest quant1.3 GB
Quick answer

NVIDIA Nemotron 3.5 Super VL 120B A12B needs about 60.3 GB of memory at IQ3_XXS (a 59.8 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 12 quants, from 1.3 GB to 131.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 0.2 GB.

NVIDIA Nemotron 3.5 Super VL 120B A12B – a vision‑language model with 1.63B parameters

NVIDIA Nemotron 3.5 Super VL 120B A12B is a vision‑language model built on the dflash architecture. It supports up to 1M context tokens and includes a C‑RADIO vision encoder. The model is available in multiple GGUF quantizations.

Good at

  • Vision‑language reasoning
  • Coding and tool use
  • Document and video understanding

Limits

  • Large memory requirement for full precision
  • No explicit language list provided
  • License is other (OpenMDW)

Best for

  • Developing AI agents that need vision and text
  • Building multimodal applications
  • Evaluating vision‑language benchmarks

Who it’s for. Developers and researchers who need a high‑capacity vision‑language model for inference or fine‑tuning. The model is suitable for commercial or non‑commercial use under the OpenMDW license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—1.3 GB 1.8 GB
Fits Get file →
IQ1_M46.1 GB (2 parts) 46.7 GB
Too big Get file →
IQ2_XXS51.1 GB (3 parts) 51.7 GB
Too big Get file →
IQ2_M55.9 GB (3 parts) 56.4 GB
Too big Get file →
Q2_K_XL57.8 GB (3 parts) 58.3 GB
Too big Get file →
IQ3_XXS59.8 GB (3 parts) 60.3 GB
Too big Get file →
Q3_K_XL65.8 GB (3 parts) 66.3 GB
Too big Get file →
—77.7 GB (3 parts) 78.2 GB
Too big Get file →
Q4_K_XL86.9 GB (3 parts) 87.4 GB
Too big Get file →
Q5_K_XL110.7 GB (4 parts) 111.2 GB
Too big Get file →
Q6_K_XL121.0 GB (4 parts) 121.5 GB
Too big Get file →
Q8_0131.6 GB (4 parts) 132.1 GB
Too big Get file →

For 8 GB VRAM, use the IQ1_M quant (46.14 GB file, ~46.7 GB memory). For 12 GB VRAM, use IQ2_XXS (51.12 GB file, ~51.7 GB memory). For 16 GB VRAM, use IQ2_M (55.88 GB file, ~56.4 GB memory).

What GPU do you need for NVIDIA Nemotron 3.5 Super VL 120B A12B?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is the main file (1.3 GB file, about 1.8 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (1.3 GB file, about 1.8 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (1.3 GB file, about 1.8 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (1.3 GB file, about 1.8 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (1.3 GB file, about 1.8 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (1.3 GB file, about 1.8 GB in use).
  • 32 GB VRAM: the best quant that fits is the main file (1.3 GB file, about 1.8 GB in use).
  • 48 GB VRAM: the best quant that fits is IQ1_M (46.1 GB file, about 46.7 GB in use).

Which NVIDIA Nemotron 3.5 Super VL 120B A12B quant should you choose?

IQ3_XXS (59.8 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

If memory is tight, the smallest file is the first one in the table at 1.3 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturedflash
Parameters1.63B
Layers5
Trained context1,048,576 tokens
KV cache (fp16)5 KB per token

Source

Quantized bynatalie5
FamilyNemotron
Licenseother
Downloads (HF)1,424
Last updated2026-10-15

Frequently asked questions about NVIDIA Nemotron 3.5 Super VL 120B A12B

How much VRAM does NVIDIA Nemotron 3.5 Super VL 120B A12B need?

About 60.3 GB at IQ3_XXS with an 8K context window. That is the 59.8 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run NVIDIA Nemotron 3.5 Super VL 120B A12B on an 8 GB GPU?

Yes, with the smaller files: the 1.3 GB file needs about 1.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

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

It depends on the quant: file is 1.3 GB, IQ1_M is 46.1 GB, IQ2_XXS is 51.1 GB, IQ2_M is 55.9 GB, Q2_K_XL is 57.8 GB, IQ3_XXS is 59.8 GB and 6 more.

What context length does NVIDIA Nemotron 3.5 Super VL 120B A12B support?

The GGUF header lists a trained context length of 1,048,576 tokens (1024K). The KV cache grows with the context you use: about 0.0 GB at 8K and 0.2 GB at 32K.

Where can I download NVIDIA Nemotron 3.5 Super VL 120B A12B GGUF?

The files are on Hugging Face in the natalie5/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does NVIDIA Nemotron 3.5 Super VL 120B A12B use?

Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run the full‑precision model on 8 GB VRAM?

No. The full‑precision file is 1.29 GB but requires ~1.8 GB memory at 8k context, which is below 8 GB but the model is 120B and not supported on 8 GB VRAM for full inference.

Which quantization is best for 12 GB VRAM?

Use IQ2_XXS or IQ2_M; both fit within 12 GB VRAM with memory estimates around 51.7 GB and 56.4 GB respectively, but IQ2_XXS is smaller.

Does the model support text‑only inference?

Yes, but it is primarily designed for vision‑language tasks and includes a vision encoder. Text‑only inference is possible but may not utilize the full model capabilities.

Similar models

Browse all →

More Nemotron models

All Nemotron →

Other tiny models

All tiny models →