WH

WhiteRabbitNeo 33B v1.5 iMat

WhiterabbitneoGGUF by dranger003Updated 2024-02-18
Download on Hugging Face
Parameters33.3B
Context16K
Layers62
Architecturellama
Smallest quant8.9 GB
Quick answer

WhiteRabbitNeo 33B v1.5 iMat 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 5 quants, from 8.9 GB (IQ2_XXS) to 19.9 GB (Q4_K_M).

WhiteRabbitNeo 33B v1.5 iMat is a 33.3B-parameter Whiterabbitneo model in GGUF format, quantized by dranger003. Its trained context length is 16K tokens. The repository has 5 quant files, from 8.9 GB (IQ2_XXS) to 19.9 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_XXS8.9 GB 11.5 GB
Too big Get file →
IQ2_XS9.9 GB 12.5 GB
Too big Get file →
IQ3_XXS13.1 GB 15.7 GB
Too big Get file →
Q3_K_M16.1 GB 18.7 GB
Too big Get file →
Q4_K_M19.9 GB 22.5 GB
Too big Get file →

What GPU do you need for WhiteRabbitNeo 33B v1.5 iMat?

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: the best quant that fits is IQ2_XXS (8.9 GB file, about 11.5 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ3_XXS (13.1 GB file, about 15.7 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).

Which WhiteRabbitNeo 33B v1.5 iMat quant should you choose?

Q4_K_M is the usual starting point for WhiteRabbitNeo 33B v1.5 iMat: it balances file size and quality well. Here it is a 19.9 GB file.

If memory is tight, the smallest file is IQ2_XXS at 8.9 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 bydranger003
Licenseother
Downloads (HF)412
Last updated2024-02-18

Frequently asked questions about WhiteRabbitNeo 33B v1.5 iMat

How much VRAM does WhiteRabbitNeo 33B v1.5 iMat 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 v1.5 iMat on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of WhiteRabbitNeo 33B v1.5 iMat GGUF?

It depends on the quant: IQ2_XXS is 8.9 GB, IQ2_XS is 9.9 GB, IQ3_XXS is 13.1 GB, Q3_K_M is 16.1 GB, Q4_K_M is 19.9 GB.

What context length does WhiteRabbitNeo 33B v1.5 iMat 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 v1.5 iMat GGUF?

The files are on Hugging Face in the dranger003/WhiteRabbitNeo-33B-v1.5-iMat.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 v1.5 iMat 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 from dranger003

All by dranger003 →

More Whiterabbitneo models

All Whiterabbitneo →

Other medium models

All medium models →