Nesi2 needs about 24.8 GB of memory at Q6_K (a 22.1 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 4 quants, from 3.2 GB (Q8_0) to 28.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.7 GB.
Nesi2 – Uncensored LLM for cybersecurity tasks
Nesi2 is a 26.9B‑parameter model built on qwen35 architecture. It is optimized for offensive and defensive security work such as penetration testing, vulnerability analysis, and secure code review. The model supports reasoning and tool‑calling.
Good at
- Penetration testing
- Vulnerability analysis
- Tool‑calling
Limits
- No vision support
- Requires 8k context for memory estimates
- Apache‑2.0 license
Best for
- Pentest automation
- Exploit development
- Secure code review
Who it’s for. Security professionals and researchers needing an uncensored, tool‑capable LLM for penetration testing and vulnerability analysis. The model is designed to run on a single GPU via llama.cpp.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 3.2 GB | 5.8 GB | Fits | Get file → | |
| Q6_K | 22.1 GB | 24.8 GB | Too big | Get file → | |
| Q6_K | 22.5 GB | 25.2 GB | Too big | Get file → | |
| Q8_0 | 28.6 GB | 31.3 GB | Too big | Get file → |
For 8‑GB VRAM, use Q8_0 (3.16 GB file, ~5.8 GB memory at 8k context). For larger budgets, Q6_K (22.08 GB file, ~24.8 GB memory) or the 22.53 GB Q6_K variant (~25.2 GB memory) are options. The 28.6 GB Q8_0 needs ~31.3 GB memory.
What GPU do you need for Nesi2?
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: the best quant that fits is Q8_0 (3.2 GB file, about 5.8 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (3.2 GB file, about 5.8 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (3.2 GB file, about 5.8 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (3.2 GB file, about 5.8 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (3.2 GB file, about 5.8 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (28.6 GB file, about 31.3 GB in use).
Which Nesi2 quant should you choose?
Q6_K (22.1 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.
If memory is tight, the smallest file is Q8_0 at 3.2 GB, with the quality trade-offs that come with fewer bits. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Nesi2
How much VRAM does Nesi2 need?
About 24.8 GB at Q6_K with an 8K context window. That is the 22.1 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 Nesi2 on an 8 GB GPU?
Yes, with Q8_0: the 3.2 GB file needs about 5.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Nesi2 GGUF?
It depends on the quant: Q8_0 is 3.2 GB, Q6_K is 22.1 GB, Q6_K is 22.5 GB, Q8_0 is 28.6 GB.
What context length does Nesi2 support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.2 GB at 8K and 8.7 GB at 32K.
Where can I download Nesi2 GGUF?
The files are on Hugging Face in the nesilabs/Nesi2 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Nesi2 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 Nesi2 on 8 GB VRAM?
Yes, the Q8_0 quant requires about 5.8 GB memory at 8k context, fitting within 8 GB VRAM. The Q6_K variants need roughly 24.8–25.2 GB and would exceed 8 GB.
Does Nesi2 support vision tasks?
No, Nesi2 does not include vision capabilities.