Nemotron 3 Nano 4B needs about 10.5 GB of memory at Q4_K_M (a 3.0 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 25 quants, from 0.0 GB to 8.0 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 28.2 GB.
Nemotron 3 Nano 4B – a compact 3.97B‑parameter language model
Nemotron 3 Nano 4B is a 3.97B‑parameter model built on the nemotron_h architecture. It supports reasoning and non‑reasoning tasks and is optimized for edge deployment. The model is available in multiple GGUF quantizations.
Good at
- Reasoning with optional trace
- Edge‑ready deployment
- Tool usage support
Limits
- Large context size requires high VRAM
- No vision capabilities
- License is NVIDIA Nemotron Open Model License
Best for
- Local voice assistants
- Gaming NPCs
- IoT automation
Who it’s for. Developers building edge AI applications that need a small, reasoning‑capable language model. The model is suitable for Jetson, GeForce RTX, and DGX Spark platforms.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 7.5 GB | Tight | Get file → | |
| IQ2_M | 2.3 GB | 9.8 GB | Too big | Get file → | |
| IQ3_XXS | 2.4 GB | 10.0 GB | Too big | Get file → | |
| Q2_K | 2.4 GB | 10.0 GB | Too big | Get file → | |
| IQ3_XS | 2.5 GB | 10.0 GB | Too big | Get file → | |
| Q3_K_S | 2.5 GB | 10.0 GB | Too big | Get file → | |
| IQ3_M | 2.5 GB | 10.0 GB | Too big | Get file → | |
| IQ4_XS | 2.6 GB | 10.1 GB | Too big | Get file → | |
| Q3_K_M | 2.6 GB | 10.1 GB | Too big | Get file → | |
| IQ4_NL | 2.6 GB | 10.1 GB | Too big | Get file → | |
| Q4_0 | 2.6 GB | 10.1 GB | Too big | Get file → | |
| Q2_K_L | 2.6 GB | 10.2 GB | Too big | Get file → | |
| Q3_K_L | 2.6 GB | 10.2 GB | Too big | Get file → | |
| Q4_1 | 2.8 GB | 10.3 GB | Too big | Get file → | |
| Q3_K_XL | 2.8 GB | 10.4 GB | Too big | Get file → | |
| Q4_K_S | 2.9 GB | 10.4 GB | Too big | Get file → | |
| Q4_K_M | 3.0 GB | 10.5 GB | Too big | Get file → | |
| Q4_K_L | 3.1 GB | 10.7 GB | Too big | Get file → | |
| Q5_K_S | 3.1 GB | 10.7 GB | Too big | Get file → | |
| Q5_K_M | 3.2 GB | 10.8 GB | Too big | Get file → | |
| Q5_K_L | 3.3 GB | 10.9 GB | Too big | Get file → | |
| Q6_K | 4.0 GB | 11.6 GB | Too big | Get file → | |
| Q6_K_L | 4.0 GB | 11.6 GB | Too big | Get file → | |
| Q8_0 | 4.2 GB | 11.8 GB | Too big | Get file → | |
| BF16 | 8.0 GB | 15.5 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_0 (file size 2.6 GB, estimated 10.1 GB memory). If 12 GB VRAM is available, Q4_K_L (3.13 GB, 10.7 GB memory) offers better quality. For 16 GB VRAM, Q6_K (4.01 GB, 11.6 GB memory) provides a balance of size and performance.
What GPU do you need for Nemotron 3 Nano 4B?
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 (0.0 GB file, about 7.5 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (4.2 GB file, about 11.8 GB in use).
- 16 GB VRAM: the best quant that fits is BF16 (8.0 GB file, about 15.5 GB in use).
Which Nemotron 3 Nano 4B quant should you choose?
Q4_K_M is the usual starting point for Nemotron 3 Nano 4B: it balances file size and quality well. Here it is a 3.0 GB file.
The Q8_0 file is 4.2 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 the first one in the table at 0.0 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 Nemotron 3 Nano 4B
How much VRAM does Nemotron 3 Nano 4B need?
About 10.5 GB at Q4_K_M with an 8K context window. That is the 3.0 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 Nano 4B on an 8 GB GPU?
Yes, with the smaller files: the 0.0 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Nemotron 3 Nano 4B GGUF?
It depends on the quant: file is 0.0 GB, IQ2_M is 2.3 GB, IQ3_XXS is 2.4 GB, Q2_K is 2.4 GB, IQ3_XS is 2.5 GB, Q3_K_S is 2.5 GB and 19 more.
What context length does Nemotron 3 Nano 4B 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 7.0 GB at 8K and 28.2 GB at 32K.
Where can I download Nemotron 3 Nano 4B GGUF?
The files are on Hugging Face in the bartowski/nvidia_Nemotron-3-Nano-4B-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 Nano 4B 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 Nemotron 3 Nano 4B on 8 GB VRAM?
Yes, the Q4_0 quantization requires about 10.1 GB memory at 8 k context, which fits in 8 GB VRAM with some overhead.
Does the model support vision tasks?
No, the model only supports text and tool usage; it has no vision capabilities.
What license applies to this model?
The model is governed by the NVIDIA Nemotron Open Model License.