ZE

zephyr-wizard-kuno-royale-BF16-merge-7B

ZephyrGGUF by grimjimUpdated 2024-08-27
Download on Hugging Face
Parameters7.24B
Context32K
Layers32
Architecturellama
Smallest quant4.4 GB
Quick answer

zephyr-wizard-kuno-royale-BF16-merge-7B needs about 6.7 GB of memory at BF16 (a 5.1 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 4 quants, from 4.4 GB (BF16) to 7.7 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

zephyr-wizard-kuno-royale-BF16-merge-7B is a 7.24B-parameter Zephyr model in GGUF format, quantized by grimjim. Its trained context length is 32K tokens. The repository has 4 quant files, from 4.4 GB (BF16) to 7.7 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
BF164.4 GB 5.9 GB
Fits Get file →
BF165.1 GB 6.7 GB
Fits Get file →
BF165.9 GB 7.5 GB
Tight Get file →
BF167.7 GB 9.3 GB
Too big Get file →

What GPU do you need for zephyr-wizard-kuno-royale-BF16-merge-7B?

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 BF16 (4.4 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is BF16 (5.9 GB file, about 7.5 GB in use).
  • 12 GB VRAM: the best quant that fits is BF16 (7.7 GB file, about 9.3 GB in use).

Which zephyr-wizard-kuno-royale-BF16-merge-7B quant should you choose?

BF16 (5.1 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

If memory is tight, the smallest file is BF16 at 4.4 GB, with the quality trade-offs that come with fewer bits. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters7.24B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized bygrimjim
FamilyZephyr
Downloads (HF)177
Last updated2024-08-27

Frequently asked questions about zephyr-wizard-kuno-royale-BF16-merge-7B

How much VRAM does zephyr-wizard-kuno-royale-BF16-merge-7B need?

About 6.7 GB at BF16 with an 8K context window. That is the 5.1 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 zephyr-wizard-kuno-royale-BF16-merge-7B on an 8 GB GPU?

Yes, with BF16: the 5.9 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of zephyr-wizard-kuno-royale-BF16-merge-7B GGUF?

It depends on the quant: BF16 is 4.4 GB, BF16 is 5.1 GB, BF16 is 5.9 GB, BF16 is 7.7 GB.

What context length does zephyr-wizard-kuno-royale-BF16-merge-7B support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download zephyr-wizard-kuno-royale-BF16-merge-7B GGUF?

The files are on Hugging Face in the grimjim/zephyr-wizard-kuno-royale-BF16-merge-7B-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 zephyr-wizard-kuno-royale-BF16-merge-7B use?

Hugging Face lists the license as cc-by-nc-4.0. 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 grimjim

All by grimjim →

More Zephyr models

All Zephyr →

Other small models

All small models →