Nex N2 Mini needs about 23.9 GB of memory at its main file (a 22.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 4 quants, from 16.5 GB to 69.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.
Nex N2 Mini – a compact, vision‑capable agentic LLM
Nex N2 Mini is a 34.7 billion‑parameter Qwen‑35‑MoE model with vision support. It is trained on 262144 context tokens and released under apache‑2.0. The model is designed for agentic workflows such as coding, research, and tool use.
Good at
- Agentic reasoning
- Vision‑enabled tasks
- Long‑horizon planning
Limits
- Requires 8 k context for memory estimates
- No official vision support in stock llama.cpp
- Large VRAM needed for BF16 variant
Best for
- Agentic coding
- Multimodal content creation
- Tool‑calling workflows
Who it’s for. Developers and researchers needing a lightweight, agentic LLM with vision capabilities. The model is open‑source and suitable for integration into custom agent frameworks.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 16.5 GB | 17.7 GB | Too big | Get file → | |
| — | 22.7 GB | 23.9 GB | Too big | Get file → | |
| — | 25.2 GB | 26.4 GB | Too big | Get file → | |
| BF16 | 69.4 GB | 70.5 GB | Too big | Get file → |
For 8 GB VRAM, use the 15.4 GB APEX‑Compact file (est. 26.4 GB memory at 8 k context). For 16 GB VRAM, the 21.3 GB APEX‑Quality file (est. 23.9 GB memory) is a good balance. If you have 70 GB VRAM, the 69.38 GB BF16 file (est. 70.5 GB memory) provides full precision.
What GPU do you need for Nex N2 Mini?
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: the best quant that fits is the main file (22.7 GB file, about 23.9 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (25.2 GB file, about 26.4 GB in use).
- 48 GB VRAM: the best quant that fits is the main file (25.2 GB file, about 26.4 GB in use).
Which Nex N2 Mini quant should you choose?
If memory is tight, the smallest file is the first one in the table at 16.5 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 Nex N2 Mini
How much VRAM does Nex N2 Mini need?
About 23.9 GB at its main file with an 8K context window. That is the 22.7 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 Nex N2 Mini on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 17.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Nex N2 Mini GGUF?
It depends on the quant: file is 16.5 GB, file is 22.7 GB, file is 25.2 GB, BF16 is 69.4 GB.
What context length does Nex N2 Mini support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.7 GB at 32K.
Where can I download Nex N2 Mini GGUF?
The files are on Hugging Face in the SC117/Nex-N2-mini-template-fix-APEX-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 Nex N2 Mini use?
Hugging Face lists the license as apache-2.0. 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 Nex N2 Mini on 8 GB VRAM?
Only the 15.4 GB APEX‑Compact file may fit, but memory usage is estimated at 26.4 GB at 8 k context, so it will not run on 8 GB VRAM.
Does the model support vision in stock llama.cpp?
The model includes vision detection, but stock llama.cpp requires a template fix; use Nex’s patched llama.cpp for full support.
What license applies to Nex N2 Mini?
The model is released under the apache‑2.0 license.