NE

Nesi2

NesiGGUF by ShaehUpdated 2026-10-25
Download on Hugging Face
Parameters26.9B
Context256K
Layers65
Architectureqwen35
Smallest quant3.2 GB
Quick answer

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 the qwen35 architecture. It is optimized for offensive and defensive cybersecurity, including penetration testing, vulnerability analysis, and secure code review. The model supports native tool‑calling and long context up to 262144 tokens.

Good at

  • Penetration testing
  • Vulnerability analysis
  • Tool‑calling

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • License is apache-2.0

Best for

  • Automated pentest agents
  • Security audit automation
  • Exploit development

Who it’s for. Security professionals and researchers needing an uncensored LLM for offensive and defensive tasks. The model is suitable for environments where native tool‑calling and long context are required.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_03.2 GB 5.8 GB
Fits Get file →
Q6_K22.1 GB 24.8 GB
Too big Get file →
Q6_K22.5 GB 25.2 GB
Too big Get file →
Q8_028.6 GB 31.3 GB
Too big Get file →

For 8 GB VRAM, use the Q8_0 quant with a file size of 3.16 GB; it requires about 5.8 GB of memory at 8 k context. If more VRAM is available, the Q6_K quant (22.08 GB) can be used, requiring roughly 24.8 GB of memory at 8 k context. The larger Q8_0 build (28.6 GB) offers higher quality but needs about 31.3 GB of 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

Architectureqwen35
Parameters26.9B
Layers65
Trained context262,144 tokens
KV cache (fp16)260 KB per token

Source

Quantized byShaeh
FamilyNesi
RepositoryShaeh/Nesi2
Licenseapache-2.0
Downloads (HF)733
Last updated2026-10-25

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 Shaeh/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 (3.16 GB) requires about 5.8 GB of VRAM at 8 k context, fitting within 8 GB.

Does Nesi2 support vision tasks?

No, the model has no vision capabilities.

Similar models

Browse all →

More from Shaeh

All by Shaeh →

More Nesi models

All Nesi →

Other medium models

All medium models →