WH

WhiteRabbitNeo 33B v1

WhiterabbitneoGGUF by mantafloppyUpdated 2024-01-13
Download on Hugging Face
Parameters33.3B
Context16K
Layers62
Architecturellama
Smallest quant19.9 GB
Quick answer

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 2 quants, from 19.9 GB (Q4_K_M) to 35.4 GB (Q8_0).

WhiteRabbitNeo 33B v1 is a 33.3B-parameter Whiterabbitneo model in GGUF format, quantized by mantafloppy. Its trained context length is 16K tokens. The repository has 2 quant files, from 19.9 GB (Q4_K_M) to 35.4 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M19.9 GB 22.5 GB
Too big Get file →
Q8_035.4 GB 38.0 GB
Too big Get file →

What GPU do you need for 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: no quant fits at an 8K context.
  • 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 Q4_K_M (19.9 GB file, about 22.5 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 33B v1 quant should you choose?

Q4_K_M is the usual starting point for 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.

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 bymantafloppy
Licenseother
Downloads (HF)177
Last updated2024-01-13

Frequently asked questions about WhiteRabbitNeo 33B v1

How much VRAM does 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 33B v1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 22.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of WhiteRabbitNeo 33B v1 GGUF?

It depends on the quant: Q4_K_M is 19.9 GB, Q8_0 is 35.4 GB.

What context length does 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 33B v1 GGUF?

The files are on Hugging Face in the mantafloppy/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 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.

Similar models

Browse all →

More Whiterabbitneo models

All Whiterabbitneo →

Other medium models

All medium models →