Nau 1.0 needs about 4.6 GB of memory at Q4_K_M (a 3.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 2 quants, from 3.7 GB (Q4_K_M) to 5.3 GB (Q8_0).
Nau 1.0 – a 4.96B Gemma 4 model with multimodal reasoning
Nau 1.0 is a 4.96B parameter Gemma 4 model that supports text, image, and audio input. It offers a 131072 token context window and is licensed under cc‑by‑nc‑sa‑4.0. The model is available in two GGUF quantizations: Q4_K_M and Q8_0.
Good at
- Multimodal reasoning
- Tool usage
- Audio support
Limits
- No vision support in this release
- Requires 4.6–6.4 GB VRAM at 8 k context
- cc‑by‑nc‑sa‑4.0 license restricts commercial use
Best for
- Local inference on laptops
- Multimodal chat applications
- Audio‑to‑text pipelines
Who it’s for. Developers needing a compact, multimodal Gemma 4 model for local deployment. The model is suitable for research and non‑commercial projects that require reasoning and tool use capabilities.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 3.7 GB | 4.6 GB | Fits | Get file → | |
| Q8_0 | 5.3 GB | 6.4 GB | Fits | Get file → |
For 8 GB VRAM, use the Q4_K_M quantization (3.69 GB file, ~4.6 GB memory). If more VRAM is available, the Q8_0 quantization (5.29 GB file, ~6.4 GB memory) provides higher precision.
What GPU do you need for Nau 1.0?
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: no quant fits at an 8K context.
- 6 GB VRAM: the best quant that fits is Q4_K_M (3.7 GB file, about 4.6 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (5.3 GB file, about 6.4 GB in use).
Which Nau 1.0 quant should you choose?
Q4_K_M is the usual starting point for Nau 1.0: it balances file size and quality well. Here it is a 3.7 GB file.
The Q8_0 file is 5.3 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Nau 1.0
How much VRAM does Nau 1.0 need?
About 4.6 GB at Q4_K_M with an 8K context window. That is the 3.7 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 Nau 1.0 on an 8 GB GPU?
Yes, with Q8_0: the 5.3 GB file needs about 6.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Nau 1.0 GGUF?
It depends on the quant: Q4_K_M is 3.7 GB, Q8_0 is 5.3 GB.
What context length does Nau 1.0 support?
The GGUF header lists a trained context length of 131,072 tokens (128K).
Where can I download Nau 1.0 GGUF?
The files are on Hugging Face in the nau-ai/Nau-1.0 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Nau 1.0 use?
Hugging Face lists the license as cc-by-nc-sa-4.0. 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 Nau 1.0 on 8 GB VRAM?
Yes, the Q4_K_M quantization requires about 4.6 GB VRAM at 8 k context, which fits within 8 GB.
Does Nau 1.0 support image input?
Yes, it supports image input with variable aspect ratio and resolution.
Is the model suitable for commercial use?
No, the cc‑by‑nc‑sa‑4.0 license prohibits commercial use.