Nemotron 3.5 Lightning Omni 30B A3B needs about 33.0 GB of memory at Q4_K_M (a 25.4 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 9 quants, from 18.7 GB (MXFP4_MOE) to 65.9 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 28.5 GB.
Nemotron 3.5 Lightning Omni 30B A3B – 30B parameter LLM with vision and audio
Nemotron 3.5 Lightning Omni 30B A3B is a 30B parameter model with 3B active parameters using a mixture‑of‑experts architecture. It supports reasoning, tools, vision, and audio modalities. The model is released in GGUF format for llama.cpp inference.
Good at
- Reasoning and tool use
- Vision and audio perception
- Large context handling
Limits
- No text‑only license restrictions
- Requires large VRAM for higher quants
- Vision and audio support gated
Best for
- Building multimodal assistants
- Fine‑tuning for specialized domains
- Deploying on high‑end GPUs
Who it’s for. Developers and researchers needing a multimodal LLM with large context and MoE efficiency. The model is suitable for commercial use and customization.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| MXFP4_MOE | 18.7 GB | 26.3 GB | Too big | Get file → | |
| IQ3_M | 18.9 GB | 26.5 GB | Too big | Get file → | |
| IQ4_XS | 19.0 GB | 26.6 GB | Too big | Get file → | |
| Q3_K_M | 20.7 GB | 28.3 GB | Too big | Get file → | |
| Q4_K_M | 25.4 GB | 33.0 GB | Too big | Get file → | |
| Q5_K_M | 27.0 GB | 34.7 GB | Too big | Get file → | |
| Q6_K | 34.9 GB | 42.5 GB | Too big | Get file → | |
| Q8_0 | 35.0 GB | 42.6 GB | Too big | Get file → | |
| BF16 | 65.9 GB | 73.5 GB | Too big | Get file → |
For 8 GB VRAM, use IQ3_M (18.86 GB file, 26.5 GB memory). For 16 GB VRAM, Q4_K_M (25.43 GB file, 33 GB memory) is a good balance. For 24 GB VRAM, Q5_K_M (27.04 GB file, 34.7 GB memory) offers higher quality.
What GPU do you need for Nemotron 3.5 Lightning Omni 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: 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: the best quant that fits is Q3_K_M (20.7 GB file, about 28.3 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 Nemotron 3.5 Lightning Omni 30B A3B quant should you choose?
Q4_K_M is the usual starting point for Nemotron 3.5 Lightning Omni 30B A3B: it balances file size and quality well. Here it is a 25.4 GB file.
The Q8_0 file is 35.0 GB, about 1.4 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 MXFP4_MOE at 18.7 GB, with the quality trade-offs that come with fewer bits. Lower bit counts mean smaller files and more quality loss.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about Nemotron 3.5 Lightning Omni 30B A3B
How much VRAM does Nemotron 3.5 Lightning Omni 30B A3B need?
About 33.0 GB at Q4_K_M with an 8K context window. That is the 25.4 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 Lightning Omni 30B A3B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 26.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Nemotron 3.5 Lightning Omni 30B A3B GGUF?
It depends on the quant: MXFP4_MOE is 18.7 GB, IQ3_M is 18.9 GB, IQ4_XS is 19.0 GB, Q3_K_M is 20.7 GB, Q4_K_M is 25.4 GB, Q5_K_M is 27.0 GB and 3 more.
What context length does Nemotron 3.5 Lightning Omni 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 Nemotron 3.5 Lightning Omni 30B A3B GGUF?
The files are on Hugging Face in the engram-ae/Nemotron-3.5-Lightning-Omni-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 Nemotron 3.5 Lightning Omni 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?
Use the IQ3_M quant, which requires about 26.5 GB memory at 8k context, so 8 GB VRAM is insufficient for full inference.
Does the model support video input?
Yes, the model includes a vision tower and supports one‑pass video with soundtrack in the released GGUF.
Is the model open source?
The model is released under the OpenMDW‑1.1 license, allowing commercial use with the provided weights.