WH

whiterabbitneo_whiterabbitneo-33b-v1

WhiterabbitneoGGUF by TheBlokeUpdated 2024-01-12
Download on Hugging Face
Parameters33.3B
Context16K
Layers62
Architecturellama
Smallest quant12.3 GB
Quick answer

whiterabbitneo_whiterabbitneo-33b-v1 needs about 22.5 GB of memory at Q4_K_M (a 19.9 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 12 quants, from 12.3 GB (Q2_K) to 35.4 GB (Q8_0).

WhiteRabbitNeo 33B v1 GGUF model for cybersecurity tasks

WhiteRabbitNeo 33B v1 is a 33.3B parameter llama architecture model quantised into GGUF format. It supports a 16384 token context and is available in multiple quantisations from Q2_K to Q8_0. The model is licensed under a restrictive agreement and is intended for local deployment via llama.cpp or compatible GUIs.

Good at

  • Cybersecurity code generation
  • Penetration testing guidance
  • Security policy drafting

Limits

  • No vision support
  • License requires user responsibility
  • Large VRAM needed for higher quants

Best for

  • Generating exploit scripts
  • Simulating attack scenarios
  • Writing security documentation

Who it’s for. Developers and security researchers who need a local LLM for offensive and defensive cybersecurity tasks. The model is suitable for those who can manage the licensing terms and have sufficient GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K12.3 GB 14.9 GB
Too big Get file →
Q3_K_S14.4 GB 17.0 GB
Too big Get file →
Q3_K_M16.1 GB 18.7 GB
Too big Get file →
Q3_K_L17.6 GB 20.1 GB
Too big Get file →
Q4_018.8 GB 21.4 GB
Too big Get file →
Q4_K_S18.9 GB 21.5 GB
Too big Get file →
Q4_K_M19.9 GB 22.5 GB
Too big Get file →
Q5_023.0 GB 25.5 GB
Too big Get file →
Q5_K_S23.0 GB 25.5 GB
Too big Get file →
Q5_K_M23.5 GB 26.1 GB
Too big Get file →
Q6_K27.4 GB 29.9 GB
Too big Get file →
Q8_035.4 GB 38.0 GB
Too big Get file →

For 8 GB VRAM, use Q4_K or Q4_K_S (file size 18.82 GB, estimated 21.4 GB memory). For 12 GB VRAM, Q5_0 or Q5_K_S (22.96 GB, 25.5 GB). For 16 GB VRAM, Q6_K (27.36 GB, 29.9 GB). Lower quants reduce VRAM but increase model size. Estimates are approximate.

What GPU do you need for whiterabbitneo_whiterabbitneo-33b-v1?

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: the best quant that fits is Q2_K (12.3 GB file, about 14.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_M (19.9 GB file, about 22.5 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (27.4 GB file, about 29.9 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (35.4 GB file, about 38.0 GB in use).

Which whiterabbitneo_whiterabbitneo-33b-v1 quant should you choose?

Q4_K_M is the usual starting point for whiterabbitneo_whiterabbitneo-33b-v1: it balances file size and quality well. Here it is a 19.9 GB file.

The Q8_0 file is 35.4 GB, about 1.8 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.

If memory is tight, the smallest file is Q2_K at 12.3 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters33.3B
Layers62
Trained context16,384 tokens
KV cache (fp16)248 KB per token

Source

Quantized byTheBloke
Licenseother
Downloads (HF)5,683
Last updated2024-01-12

Frequently asked questions about whiterabbitneo_whiterabbitneo-33b-v1

How much VRAM does whiterabbitneo_whiterabbitneo-33b-v1 need?

About 22.5 GB at Q4_K_M with an 8K context window. That is the 19.9 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 whiterabbitneo_whiterabbitneo-33b-v1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 14.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of whiterabbitneo_whiterabbitneo-33b-v1 GGUF?

It depends on the quant: Q2_K is 12.3 GB, Q3_K_S is 14.4 GB, Q3_K_M is 16.1 GB, Q3_K_L is 17.6 GB, Q4_0 is 18.8 GB, Q4_K_S is 18.9 GB and 6 more.

What context length does whiterabbitneo_whiterabbitneo-33b-v1 support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 2.1 GB at 8K and 4.2 GB at 16K.

Where can I download whiterabbitneo_whiterabbitneo-33b-v1 GGUF?

The files are on Hugging Face in the TheBloke/WhiteRabbitNeo-33B-v1-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 whiterabbitneo_whiterabbitneo-33b-v1 use?

Hugging Face lists the license as other. 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?

Yes, using Q4_K or Q4_K_S quantisations which estimate 21.4 GB VRAM at 8k context. The file size is 18.82 GB.

Does the model support image inputs?

No, the model has no vision capabilities.

What license applies to this model?

The model is under a restrictive license that requires users to assume responsibility for use and outcomes.

Other GGUFs of WhiteRabbitNeo-33B-v1

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Whiterabbitneo models

All Whiterabbitneo →

Other medium models

All medium models →