LL

KSJ llama

LlamaGGUF by CatOwlUpdated 2024-10-15
Download on Hugging Face
Parameters8.03B
Context8K
Layers32
Architecturellama
Smallest quant16.1 GB
Quick answer

KSJ llama needs about 17.6 GB of memory at its main file (a 16.1 GB file) with an 8K context window, so it fits on a 24 GB GPU.

KSJ llama is a 8.03B-parameter Llama model in GGUF format, quantized by CatOwl. Its trained context length is 8K tokens. The repository has 1 quant file, from 16.1 GB to 16.1 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—16.1 GB 17.6 GB
Too big Get file →

What GPU do you need for KSJ llama?

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 the main file (16.1 GB file, about 17.6 GB in use).

Specifications

Architecture from the GGUF header

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

Source

Quantized byCatOwl
FamilyLlama
Licensemit
Downloads (HF)3
Last updated2024-10-15

Frequently asked questions about KSJ llama

How much VRAM does KSJ llama need?

About 17.6 GB at its main file with an 8K context window. That is the 16.1 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 KSJ llama on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 17.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of KSJ llama GGUF?

It depends on the quant: file is 16.1 GB.

What context length does KSJ llama 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 KSJ llama GGUF?

The files are on Hugging Face in the CatOwl/KSJ_llama_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 KSJ llama 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 Llama models

All Llama →

Other small models

All small models →