NVIDIA Nemotron 3.5 Lightning 30B A3B needs about 22.1 GB of memory at its main file (a 19.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 4 quants, from 0.1 GB to 65.9 GB (BF16).
NVIDIA Nemotron 3.5 Lightning 30B A3B – 32.9B parameter LLM
NVIDIA Nemotron 3.5 Lightning 30B A3B is a 32.9B parameter large language model. It is released in GGUF format and supports quantization for inference. The model is licensed under OpenMDW-1.1 and is ready for commercial use.
Good at
- High‑quality text generation
- Domain adaptation
- Customizable inference
Limits
- No vision support
- Requires large VRAM for full precision
- License restricts redistribution
Best for
- Fine‑tuning for specialized agents
- Deploying on high‑end GPUs
- Research on MoE architectures
Who it’s for. Developers and researchers who need a large, open‑source LLM with a hybrid Mamba‑2 and MoE architecture. The model is suitable for teams that can handle the memory requirements and comply with the OpenMDW‑1.1 license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.1 GB | 0.6 GB | Fits | Get file → | |
| — | 19.3 GB | 22.1 GB | Too big | Get file → | |
| — | 19.3 GB | 22.1 GB | Too big | Get file → | |
| BF16 | 65.9 GB | 74.3 GB | Too big | Get file → |
For 8 GB VRAM, the 0.06 GB unknown quant is the only viable option, using about 0.6 GB of memory at 8 k context. For 16 GB VRAM, the 19.32 GB unknown quant uses about 22.1 GB of memory, which is close to the limit. The BF16 65.85 GB quant requires roughly 74.3 GB of memory and is only suitable for very large GPU setups.
What GPU do you need for NVIDIA Nemotron 3.5 Lightning 30B A3B?
These figures add the file size, an fp16 KV cache at an 8K context window 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 (0.1 GB file, about 0.6 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 0.6 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 0.6 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 0.6 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 0.6 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (19.3 GB file, about 22.1 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (19.3 GB file, about 22.1 GB in use).
- 48 GB VRAM: the best quant that fits is the main file (19.3 GB file, about 22.1 GB in use).
Which NVIDIA Nemotron 3.5 Lightning 30B A3B quant should you choose?
If memory is tight, the smallest file is the first one in the table at 0.1 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
Source
Frequently asked questions about NVIDIA Nemotron 3.5 Lightning 30B A3B
How much VRAM does NVIDIA Nemotron 3.5 Lightning 30B A3B need?
About 22.1 GB at its main file with an 8K context window. That is the 19.3 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 Lightning 30B A3B on an 8 GB GPU?
Yes, with the smaller files: the 0.1 GB file needs about 0.6 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 Lightning 30B A3B GGUF?
It depends on the quant: file is 0.1 GB, file is 19.3 GB, file is 19.3 GB, BF16 is 65.9 GB.
Where can I download NVIDIA Nemotron 3.5 Lightning 30B A3B GGUF?
The files are on Hugging Face in the DrMoriarty0/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-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 Lightning 30B A3B use?
Hugging Face lists the license as openmdw-1.1. 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 model on 8 GB VRAM?
Only the 0.06 GB unknown quant can be loaded, using about 0.6 GB of memory at 8 k context.
What is the memory requirement for the BF16 quant?
The BF16 quant is 65.85 GB and requires about 74.3 GB of memory at 8 k context.
Does the model support vision tasks?
No, the model has no vision capabilities.