NE

NVIDIA-Nemotron-3.5-Super-VL-120B-A12B

NemotronGGUF by ggml-orgUpdated 2026-10-26
Download on Hugging Face
Parameters1.66B
Context1024K
Layers5
Architecturedflash
Smallest quant1.4 GB
Quick answer

NVIDIA-Nemotron-3.5-Super-VL-120B-A12B needs about 8.7 GB of memory at BF16 (a 8.0 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 8 quants, from 1.4 GB to 241.5 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 0.7 GB.

NVIDIA Nemotron 3.5 Super VL 120B A12B – vision‑language model with 1.66B 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
  • Long‑context understanding
  • Tool‑calling

Limits

  • Requires 1M token context support
  • No text‑only usage limits specified
  • License is other

Best for

  • Multimodal document analysis
  • Video understanding tasks
  • AI agent development

Who it’s for. Developers and researchers needing a large vision‑language model for complex reasoning and multimodal tasks. The model is suitable for commercial or non‑commercial use under the OpenMDW License Agreement.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—1.4 GB 2.0 GB
Fits Get file →
Q4_02.3 GB 2.9 GB
Fits Get file →
Q8_04.3 GB 4.9 GB
Fits Get file →
BF168.0 GB 8.7 GB
Too big Get file →
Q4_071.9 GB 72.6 GB
Too big Get file →
—76.9 GB 77.6 GB
Too big Get file →
Q8_0128.5 GB 129.1 GB
Too big Get file →
BF16241.5 GB 242.2 GB
Too big Get file →

For 8 GB VRAM, use the Q4_0 quantization (file size 2.27 GB, estimated memory 2.9 GB at 8 k context). For 16 GB VRAM, Q8_0 (4.28 GB, 4.9 GB). For 32 GB VRAM, BF16 (8.04 GB, 8.7 GB). Larger quants require more 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 Q4_0 (2.3 GB file, about 2.9 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (4.3 GB file, about 4.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.3 GB file, about 4.9 GB in use).
  • 12 GB VRAM: the best quant that fits is BF16 (8.0 GB file, about 8.7 GB in use).
  • 16 GB VRAM: the best quant that fits is BF16 (8.0 GB file, about 8.7 GB in use).
  • 24 GB VRAM: the best quant that fits is BF16 (8.0 GB file, about 8.7 GB in use).
  • 32 GB VRAM: the best quant that fits is BF16 (8.0 GB file, about 8.7 GB in use).
  • 48 GB VRAM: the best quant that fits is BF16 (8.0 GB file, about 8.7 GB in use).

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

BF16 (8.0 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

If memory is tight, the smallest file is the first one in the table at 1.4 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
Parameters1.66B
Layers5
Trained context1,048,576 tokens
KV cache (fp16)20 KB per token

Source

Quantized byggml-org
FamilyNemotron
Licenseother
Downloads (HF)53,913
Last updated2026-10-26

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 8.7 GB at BF16 with an 8K context window. That is the 8.0 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 Q8_0: the 4.3 GB file needs about 4.9 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 1.4 GB, Q4_0 is 2.3 GB, Q8_0 is 4.3 GB, BF16 is 8.0 GB, Q4_0 is 71.9 GB, file is 76.9 GB and 2 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 0.2 GB at 8K and 0.7 GB at 32K.

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

The files are on Hugging Face in the ggml-org/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 NVIDIA‑Nemotron‑3.5‑Super‑VL‑120B‑A12B on 8 GB VRAM?

Yes, using the Q4_0 quantization which requires approximately 2.9 GB of VRAM at 8 k context.

Does this model support text‑only inference?

The model includes vision capabilities but can be used for text inference; no restriction is noted.

What is the maximum context length?

The model supports up to 1M tokens of context.

Other GGUFs of NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16

Similar models

Browse all →

More from ggml-org

All by ggml-org →

More Nemotron models

All Nemotron →

Other tiny models

All tiny models →