ME

merged 13b

MergedGGUF by aus-396Updated 2024-06-23
Download on Hugging Face
Parameters13B
Context4K
Layers40
Architecturellama
Smallest quant13.8 GB
Quick answer

merged 13b needs about 21.0 GB of memory at its main file (a 13.8 GB file) with an 8K context window, so it fits on a 24 GB GPU.

merged 13b is a 13B-parameter Merged model in GGUF format, quantized by aus-396. Its trained context length is 4K tokens. The repository has 1 quant file, from 13.8 GB to 13.8 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—13.8 GB 17.7 GB
Too big Get file →

What GPU do you need for merged 13b?

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 (13.8 GB file, about 21.0 GB in use).

Specifications

Architecture from the GGUF header

Architecturellama
Parameters13B
Layers40
Trained context4,096 tokens
KV cache (fp16)800 KB per token

Source

Quantized byaus-396
FamilyMerged
Licensemit
Downloads (HF)6
Last updated2024-06-23

Frequently asked questions about merged 13b

How much VRAM does merged 13b need?

About 21.0 GB at its main file with an 8K context window. That is the 13.8 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 merged 13b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 21.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of merged 13b GGUF?

It depends on the quant: file is 13.8 GB.

What context length does merged 13b support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 6.7 GB at 8K and 3.4 GB at 4K.

Where can I download merged 13b GGUF?

The files are on Hugging Face in the aus-396/merged-13b repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does merged 13b 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 aus-396

All by aus-396 →

More Merged models

All Merged →

Other medium models

All medium models →