NVIDIA Nemotron 3.5 Lightning 30B A3B needs about 33.1 GB of memory at Q4_K_M (a 25.5 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 30 quants, from 0.1 GB to 65.9 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 28.5 GB.
NVIDIA Nemotron 3.5 Lightning 30B A3B – a 30B parameter Mixture‑of‑Experts LLM in GGUF format
NVIDIA Nemotron 3.5 Lightning 30B A3B is a 30 billion‑parameter model with 3 billion active parameters. It uses a hybrid nemotron_h_moe architecture and supports 1 048 576‑token context. The GGUF checkpoint is available in multiple quantizations.
Good at
- Large context handling
- Mixture‑of‑Experts efficiency
- Versatile quantization options
Limits
- Requires high VRAM for large quants
- No vision or audio support
- License is other – check terms
Best for
- Custom fine‑tuning on domain data
- Low‑latency inference with small quants
- Research on MoE architectures
Who it’s for. Engineers and researchers needing a large, flexible LLM with Mixture‑of‑Experts capability. The model is suitable for commercial use under its license terms.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.1 GB | 7.7 GB | Tight | Get file → | |
| Q4_0 | 1.2 GB | 8.8 GB | Too big | Get file → | |
| Q8_0 | 2.2 GB | 9.8 GB | Too big | Get file → | |
| IQ2_XXS | 18.8 GB | 26.5 GB | Too big | Get file → | |
| IQ2_XS | 18.8 GB | 26.5 GB | Too big | Get file → | |
| IQ2_S | 18.9 GB | 26.5 GB | Too big | Get file → | |
| IQ2_M | 18.9 GB | 26.5 GB | Too big | Get file → | |
| Q2_K | 18.9 GB | 26.5 GB | Too big | Get file → | |
| IQ4_XS | 18.9 GB | 26.5 GB | Too big | Get file → | |
| IQ4_NL | 18.9 GB | 26.5 GB | Too big | Get file → | |
| Q3_K_S | 18.9 GB | 26.6 GB | Too big | Get file → | |
| Q4_0 | 19.1 GB | 26.7 GB | Too big | Get file → | |
| Q2_K_L | 19.1 GB | 26.7 GB | Too big | Get file → | |
| IQ3_XXS | 19.8 GB | 27.4 GB | Too big | Get file → | |
| IQ3_XS | 19.8 GB | 27.4 GB | Too big | Get file → | |
| Q3_K_M | 19.8 GB | 27.4 GB | Too big | Get file → | |
| Q3_K_L | 20.2 GB | 27.9 GB | Too big | Get file → | |
| IQ3_M | 20.3 GB | 27.9 GB | Too big | Get file → | |
| Q3_K_XL | 20.4 GB | 28.0 GB | Too big | Get file → | |
| Q4_1 | 20.9 GB | 28.5 GB | Too big | Get file → | |
| Q4_K_S | 23.2 GB | 30.8 GB | Too big | Get file → | |
| Q5_K_S | 24.8 GB | 32.4 GB | Too big | Get file → | |
| Q4_K_M | 25.5 GB | 33.1 GB | Too big | Get file → | |
| Q4_K_L | 25.6 GB | 33.2 GB | Too big | Get file → | |
| Q5_K_M | 27.0 GB | 34.6 GB | Too big | Get file → | |
| Q5_K_L | 27.1 GB | 34.7 GB | Too big | Get file → | |
| Q6_K | 34.3 GB | 41.9 GB | Too big | Get file → | |
| Q6_K_L | 34.3 GB | 41.9 GB | Too big | Get file → | |
| Q8_0 | 35.0 GB | 42.6 GB | Too big | Get file → | |
| BF16 | 65.9 GB (2 parts) | 73.5 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_0 (1.16 GB file, ~8.8 GB VRAM). For 16 GB VRAM, Q8_0 (2.18 GB file, ~9.8 GB VRAM) or Q4_K_M (25.48 GB file, ~33.1 GB VRAM) if more memory is available. For 32 GB VRAM, Q5_K_L (27.07 GB file, ~34.7 GB VRAM) offers a good trade‑off. All estimates are approximate.
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 (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: the best quant that fits is the main file (0.1 GB file, about 7.7 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (2.2 GB file, about 9.8 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (2.2 GB file, about 9.8 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (2.2 GB file, about 9.8 GB in use).
- 32 GB VRAM: the best quant that fits is Q4_K_S (23.2 GB file, about 30.8 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (35.0 GB file, about 42.6 GB in use).
Which NVIDIA Nemotron 3.5 Lightning 30B A3B quant should you choose?
Q4_K_M is the usual starting point for NVIDIA Nemotron 3.5 Lightning 30B A3B: it balances file size and quality well. Here it is a 25.5 GB file.
The Q8_0 file is 2.2 GB, about 0.1 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
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
Frequently asked questions about NVIDIA Nemotron 3.5 Lightning 30B A3B
How much VRAM does NVIDIA Nemotron 3.5 Lightning 30B A3B need?
About 33.1 GB at Q4_K_M with an 8K context window. That is the 25.5 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 7.7 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, Q4_0 is 1.2 GB, Q8_0 is 2.2 GB, IQ2_XXS is 18.8 GB, IQ2_XS is 18.8 GB, IQ2_S is 18.9 GB and 24 more.
What context length does NVIDIA Nemotron 3.5 Lightning 30B A3B 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 7.1 GB at 8K and 28.5 GB at 32K.
Where can I download NVIDIA Nemotron 3.5 Lightning 30B A3B GGUF?
The files are on Hugging Face in the bartowski/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 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 8 GB VRAM?
Yes, using the Q4_0 quantization which requires about 8.8 GB VRAM at 8k context.
Does this model support vision or audio inputs?
No, it only supports text input.
What license applies to this model?
The model is governed by the OpenMDW‑1.1 license, which allows commercial use.