ZE

orpo zephyr 8x22 EdgeQuants

ZephyrGGUF by nistenUpdated 2024-04-12
Download on Hugging Face
Parameters141B
Context64K
Layers56
Architecturellama
Smallest quant46.2 GB
Quick answer

orpo zephyr 8x22 EdgeQuants needs about 48.5 GB of memory at its main file (a 46.2 GB file) with an 8K context window, which is more than a 48 GB GPU holds. Longer context needs more: at 32K tokens the KV cache alone adds about 7.5 GB.

orpo zephyr 8x22 EdgeQuants is a 141B-parameter Zephyr model in GGUF format, quantized by nisten. Its trained context length is 64K tokens. The repository has 1 quant file, from 46.2 GB to 46.2 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—46.2 GB 48.5 GB
Too big Get file →

What GPU do you need for orpo zephyr 8x22 EdgeQuants?

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: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: no quant fits at an 8K context.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters141B (approximate, mixture of experts)
Layers56
Trained context65,536 tokens
KV cache (fp16)224 KB per token

Source

Quantized bynisten
FamilyZephyr
Licenseapache-2.0
Downloads (HF)29
Last updated2024-04-12

Frequently asked questions about orpo zephyr 8x22 EdgeQuants

How much VRAM does orpo zephyr 8x22 EdgeQuants need?

About 48.5 GB at its main file with an 8K context window. That is the 46.2 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 orpo zephyr 8x22 EdgeQuants on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 48.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of orpo zephyr 8x22 EdgeQuants GGUF?

It depends on the quant: file is 46.2 GB.

What context length does orpo zephyr 8x22 EdgeQuants support?

The GGUF header lists a trained context length of 65,536 tokens (64K). The KV cache grows with the context you use: about 1.9 GB at 8K and 7.5 GB at 32K.

Where can I download orpo zephyr 8x22 EdgeQuants GGUF?

The files are on Hugging Face in the nisten/orpo-zephyr-8x22-EdgeQuants-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 orpo zephyr 8x22 EdgeQuants 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.

Other GGUFs of zephyr-orpo-141b-A35b-v0.1

Similar models

Browse all →

More from nisten

All by nisten →

More Zephyr models

All Zephyr →

Other large models

All large models →