Huihui Nex N2 Mini Abliterated needs about 24.0 GB of memory at its main file (a 22.8 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.
Huihui Nex N2 Mini Abliterated – Vision‑capable, abliterated MoE model
Huihui Nex N2 Mini Abliterated is a 34.7B‑parameter Qwen‑3.5‑MoE model with 262144‑token context. It supports vision and agentic tasks and is released under apache‑2.0. The model is abliterated and should be used only in controlled environments.
Good at
- Vision processing
- Agentic reasoning
- Large context handling
Limits
- Abliterated – may produce sensitive content
- Requires patched llama.cpp for thinking mode
- No safety filtering
Best for
- Research on vision‑enabled LLMs
- Controlled testing of agentic behavior
- Exploring MoE performance
Who it’s for. Researchers and developers needing a large‑context, vision‑capable MoE model for experimentation. The abliterated nature makes it unsuitable for public or production use.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 16.5 GB | 17.7 GB | Too big | Get file → | |
| — | 22.8 GB | 24.0 GB | Too big | Get file → | |
| — | 25.3 GB | 26.5 GB | Too big | Get file → | |
| BF16 | 69.4 GB | 70.5 GB | Too big | Get file → |
For 8 GB VRAM, use the 16.54 GB file (est. 17.7 GB memory at 8 k context). For 16 GB VRAM, the 22.82 GB file (est. 24 GB) is suitable. The 25.34 GB file (est. 26.5 GB) fits 24 GB VRAM. The BF16 69.38 GB file requires 70.5 GB memory and is only for high‑end GPUs.
What GPU do you need for Huihui Nex N2 Mini Abliterated?
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 (22.8 GB file, about 24.0 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (25.3 GB file, about 26.5 GB in use).
- 48 GB VRAM: the best quant that fits is the main file (25.3 GB file, about 26.5 GB in use).
Which Huihui Nex N2 Mini Abliterated 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
Frequently asked questions about Huihui Nex N2 Mini Abliterated
How much VRAM does Huihui Nex N2 Mini Abliterated need?
About 24.0 GB at its main file with an 8K context window. That is the 22.8 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 Huihui Nex N2 Mini Abliterated 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 Huihui Nex N2 Mini Abliterated GGUF?
It depends on the quant: file is 16.5 GB, file is 22.8 GB, file is 25.3 GB, BF16 is 69.4 GB.
What context length does Huihui Nex N2 Mini Abliterated 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 Huihui Nex N2 Mini Abliterated GGUF?
The files are on Hugging Face in the SC117/Huihui-Nex-N2-mini-abliterated-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 Huihui Nex N2 Mini Abliterated 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 this model on 8 GB VRAM?
The 16.54 GB file requires about 17.7 GB memory at 8 k context, so 8 GB VRAM is insufficient.
Does it support vision tasks?
Yes, the model has detected vision abilities and is designed for vision processing.
Is it safe for public deployment?
No. It is abliterated, may generate sensitive content, and is recommended only for research or controlled environments.