GS

GSUltraforshadowKall108

GsultraforshadowkallGGUF by UniLLMerUpdated 2024-12-06
Download on Hugging Face
Parameters18.7B
Context10K
Layers81
Architecturellama
Smallest quant13.3 GB
Quick answer

GSUltraforshadowKall108 needs about 16.5 GB of memory at Q5_K_M (a 13.3 GB file) with an 8K context window, so it fits on a 24 GB GPU.

GSUltraforshadowKall108 is a 18.7B-parameter Gsultraforshadowkall model in GGUF format, quantized by UniLLMer. Its trained context length is 10K tokens. The repository has 1 quant file, from 13.3 GB (Q5_K_M) to 13.3 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M13.3 GB 16.5 GB
Too big Get file →

What GPU do you need for GSUltraforshadowKall108?

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 Q5_K_M (13.3 GB file, about 16.5 GB in use).

Which GSUltraforshadowKall108 quant should you choose?

Q5_K_M (13.3 GB) is the middle option in this repository. 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
Parameters18.7B
Layers81
Trained context10,020 tokens
KV cache (fp16)324 KB per token

Source

Quantized byUniLLMer
Licenseapache-2.0
Downloads (HF)43
Last updated2024-12-06

Frequently asked questions about GSUltraforshadowKall108

How much VRAM does GSUltraforshadowKall108 need?

About 16.5 GB at Q5_K_M with an 8K context window. That is the 13.3 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 GSUltraforshadowKall108 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 16.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of GSUltraforshadowKall108 GGUF?

It depends on the quant: Q5_K_M is 13.3 GB.

What context length does GSUltraforshadowKall108 support?

The GGUF header lists a trained context length of 10,020 tokens (10K). The KV cache grows with the context you use: about 2.7 GB at 8K and 3.3 GB at 10K.

Where can I download GSUltraforshadowKall108 GGUF?

The files are on Hugging Face in the UniLLMer/GSUltraforshadowKall108 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does GSUltraforshadowKall108 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.

Similar models

Browse all →

More from UniLLMer

All by UniLLMer →

Other medium models

All medium models →