GH

Ghost 8b Beta

GhostGGUF by ZeroWwUpdated 2024-07-25
Download on Hugging Face
Parameters8.03B
Context8K
Layers32
Architecturellama
Smallest quant7.0 GB
Quick answer

Ghost 8b Beta needs about 10.1 GB of memory at its main file (a 8.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 5 quants, from 7.0 GB (Q5_K) to 16.1 GB (F16).

Ghost 8b Beta is a 8.03B-parameter Ghost model in GGUF format, quantized by ZeroWw. Its trained context length is 8K tokens. The repository has 5 quant files, from 7.0 GB (Q5_K) to 16.1 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K7.0 GB 8.6 GB
Too big Get file →
Q6_K7.8 GB 9.4 GB
Too big Get file →
—8.5 GB 10.1 GB
Too big Get file →
Q8_09.5 GB 11.1 GB
Too big Get file →
F1616.1 GB 17.6 GB
Too big Get file →

What GPU do you need for Ghost 8b Beta?

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 Q8_0 (9.5 GB file, about 11.1 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (9.5 GB file, about 11.1 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (16.1 GB file, about 17.6 GB in use).

Which Ghost 8b Beta quant should you choose?

If memory is tight, the smallest file is Q5_K at 7.0 GB, with the quality trade-offs that come with fewer bits. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters8.03B
Layers32
Trained context8,192 tokens
KV cache (fp16)128 KB per token

Source

Quantized byZeroWw
FamilyGhost
Licensemit
Downloads (HF)46
Last updated2024-07-25

Frequently asked questions about Ghost 8b Beta

How much VRAM does Ghost 8b Beta need?

About 10.1 GB at its main file with an 8K context window. That is the 8.5 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 Ghost 8b Beta on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Ghost 8b Beta GGUF?

It depends on the quant: Q5_K is 7.0 GB, Q6_K is 7.8 GB, file is 8.5 GB, Q8_0 is 9.5 GB, F16 is 16.1 GB.

What context length does Ghost 8b Beta support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.1 GB at 8K and 1.1 GB at 8K.

Where can I download Ghost 8b Beta GGUF?

The files are on Hugging Face in the ZeroWw/ghost-8b-beta-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 Ghost 8b Beta use?

Hugging Face lists the license as mit. 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 ZeroWw

All by ZeroWw →

More Ghost models

All Ghost →

Other small models

All small models →