Nemotron 3.5 Super 120B A12B NVFP4 Strata Blackwell needs about 84.1 GB of memory at its main file (a 71.6 GB file) with an 8K context window, which is more than a 48 GB GPU holds. Longer context needs more: at 32K tokens the KV cache alone adds about 47.8 GB.
Nemotron 3.5 Super 120B A12B NVFP4 Strata Blackwell – a large vision‑language model
Nemotron 3.5 Super 120B A12B NVFP4 Strata Blackwell is a 124 billion‑parameter model with 12 billion active parameters. It supports up to 1 048 576 context tokens and includes reasoning, tools, and vision capabilities. The model is quantized with NVFP4 and is available as a single 71.62 GB GGUF file.
Good at
- Reasoning
- Tool use
- Vision
Limits
- Requires RTX 50‑series GPU
- Approx. 84.1 GB VRAM at 8 k context
- Large file size 71.62 GB
Best for
- Complex reasoning tasks
- Automated tool‑based workflows
- Image‑based question answering
Who it’s for. Developers building AI agents that need advanced reasoning, tool integration, and vision support on high‑end NVIDIA GPUs. The model is suitable for both commercial and non‑commercial use.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 71.6 GB (2 parts) | 84.1 GB | Too big | Get file → |
The only available quant is the 71.62 GB NVFP4 GGUF file. It requires roughly 84.1 GB VRAM at 8 k context, so a high‑end GPU with at least 16 GB VRAM and ample system RAM is recommended. No other quantizations are provided.
What GPU do you need for Nemotron 3.5 Super 120B A12B NVFP4 Strata Blackwell?
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.
Specifications
Architecture from the GGUF header
Frequently asked questions about Nemotron 3.5 Super 120B A12B NVFP4 Strata Blackwell
How much VRAM does Nemotron 3.5 Super 120B A12B NVFP4 Strata Blackwell need?
About 84.1 GB at its main file with an 8K context window. That is the 71.6 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 Nemotron 3.5 Super 120B A12B NVFP4 Strata Blackwell on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 84.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Nemotron 3.5 Super 120B A12B NVFP4 Strata Blackwell GGUF?
It depends on the quant: file is 71.6 GB.
What context length does Nemotron 3.5 Super 120B A12B NVFP4 Strata Blackwell 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 Nemotron 3.5 Super 120B A12B NVFP4 Strata Blackwell GGUF?
The files are on Hugging Face in the Cudecnik/Nemotron-3.5-Super-120B-A12B-NVFP4-Strata-Blackwell repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Nemotron 3.5 Super 120B A12B NVFP4 Strata Blackwell 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 this model on an 8 GB VRAM GPU?
No, the model requires significantly more VRAM than 8 GB.
Does the model support vision tasks?
Yes, it includes vision support via strata‑vision and Unsloth's mmproj-BF16.gguf.
How many experts does the model use?
It uses 12 billion active parameters as experts.