LL

llamarizer

LlamaGGUF by masta-g3Updated 2023-09-16
Download on Hugging Face
Parameters13B
Context16K
Layers32
Architecturellama
Smallest quant7.2 GB
Quick answer

llamarizer needs about 12.0 GB of memory at its main file (a 7.2 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 2 quants, from 7.2 GB to 13.8 GB.

llamarizer is a 13B-parameter Llama model in GGUF format, quantized by masta-g3. Its trained context length is 16K tokens. The repository has 2 quant files, from 7.2 GB to 13.8 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—7.2 GB 12.0 GB
Too big Get file →
—13.8 GB 18.6 GB
Too big Get file →

What GPU do you need for llamarizer?

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 the main file (7.2 GB file, about 12.0 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (7.2 GB file, about 12.0 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (13.8 GB file, about 18.6 GB in use).

Specifications

Architecture from the GGUF header

Architecturellama
Parameters13B
Layers32
Trained context16,384 tokens
KV cache (fp16)512 KB per token

Source

Quantized bymasta-g3
FamilyLlama
Downloads (HF)45
Last updated2023-09-16

Frequently asked questions about llamarizer

How much VRAM does llamarizer need?

About 12.0 GB at its main file with an 8K context window. That is the 7.2 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 llamarizer on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of llamarizer GGUF?

It depends on the quant: file is 7.2 GB, file is 13.8 GB.

What context length does llamarizer support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 4.3 GB at 8K and 8.6 GB at 16K.

Where can I download llamarizer GGUF?

The files are on Hugging Face in the masta-g3/llamarizer-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More Llama models

All Llama →

Other medium models

All medium models →