NVIDIA-Nemotron-3.5-Super-VL-120B-A12B needs about 77.8 GB of memory at IQ3_XXS (a 65.3 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 12 quants, from 45.7 GB (Q2_0) to 131.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 47.8 GB.
NVIDIA Nemotron 3.5 Super VL 120B-A12B – a large vision‑language model with MoE
NVIDIA Nemotron 3.5 Super VL 120B-A12B is a 124 B parameter vision‑language model with 12 B active parameters. It supports up to 1 M tokens of context and includes a C‑RADIO vision encoder. The model is released under the OpenMDW License Agreement.
Good at
- Vision‑language reasoning
- Long‑context understanding
- Tool‑calling
Limits
- Requires large VRAM for high‑quality quants
- No native text‑only mode
- License terms restrict commercial use
Best for
- Multimodal document analysis
- Video understanding tasks
- Agentic reasoning with vision
Who it’s for. Developers building vision‑enabled AI agents who need large context and MoE efficiency. The model is suitable for research and commercial deployment under the OpenMDW license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_0 | 45.7 GB | 58.2 GB | Too big | Get file → | |
| Q2_0 | 51.0 GB | 63.5 GB | Too big | Get file → | |
| Q2_0 | 55.8 GB (2 parts) | 68.3 GB | Too big | Get file → | |
| Q2_0 | 57.4 GB (2 parts) | 69.9 GB | Too big | Get file → | |
| IQ2_M | 59.3 GB (2 parts) | 71.8 GB | Too big | Get file → | |
| IQ3_XXS | 65.3 GB (2 parts) | 77.8 GB | Too big | Get file → | |
| IQ3_M | 70.0 GB (2 parts) | 82.4 GB | Too big | Get file → | |
| IQ4_NL | 74.8 GB (2 parts) | 87.3 GB | Too big | Get file → | |
| Q4_K_S | 86.9 GB (2 parts) | 99.3 GB | Too big | Get file → | |
| Q5_K_S | 110.6 GB (3 parts) | 123.0 GB | Too big | Get file → | |
| Q6_K | 120.0 GB (3 parts) | 132.4 GB | Too big | Get file → | |
| Q8_0 | 131.6 GB (3 parts) | 144.0 GB | Too big | Get file → |
For 8 GB VRAM, use the Q2_0 quant (file size 45.72 GB, estimated 58.2 GB memory at 8 k context). For 12 GB VRAM, the Q4_K_S quant (file size 86.9 GB, estimated 99.3 GB memory) is a good balance. Higher quants such as Q6_K or Q8_0 require 120 GB or more VRAM and are not recommended for limited hardware.
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: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: no quant fits at an 8K context.
- 48 GB VRAM: no quant fits at an 8K context.
Which NVIDIA-Nemotron-3.5-Super-VL-120B-A12B quant should you choose?
IQ3_XXS (65.3 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 Q2_0 at 45.7 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
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 77.8 GB at IQ3_XXS with an 8K context window. That is the 65.3 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?
Not at an 8K context. The smallest file needs about 58.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of NVIDIA-Nemotron-3.5-Super-VL-120B-A12B GGUF?
It depends on the quant: Q2_0 is 45.7 GB, Q2_0 is 51.0 GB, Q2_0 is 55.8 GB, Q2_0 is 57.4 GB, IQ2_M is 59.3 GB, IQ3_XXS is 65.3 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 11.9 GB at 8K and 47.8 GB at 32K.
Where can I download NVIDIA-Nemotron-3.5-Super-VL-120B-A12B GGUF?
The files are on Hugging Face in the AtomicChat/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 on 8 GB VRAM?
Only the lowest‑quality Q2_0 quant can fit, but it still requires about 58.2 GB memory at 8 k context, so 8 GB VRAM is insufficient.
Does this model support text‑only inference?
The model includes vision capabilities but can be used for text only; however, the quantized files are optimized for vision tasks.
What license applies to this model?
The model is governed by the OpenMDW License Agreement, version 1.1.