VI

Vicuna 13B v1.3

VicunaGGUF by gotzmannUpdated 2023-10-23
Download on Hugging Face
Parameters13B
Context4K
Layers40
Architecturellama
Smallest quant7.4 GB
Quick answer

Vicuna 13B v1.3 needs about 16.2 GB of memory at its main file (a 9.0 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 5 quants, from 7.4 GB to 10.7 GB.

Vicuna 13B v1.3 is a 13B-parameter Vicuna model in GGUF format, quantized by gotzmann. Its trained context length is 4K tokens. The repository has 5 quant files, from 7.4 GB to 10.7 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—7.4 GB 11.2 GB
Too big Get file →
—7.9 GB 11.7 GB
Too big Get file →
—9.0 GB 12.8 GB
Too big Get file →
—9.2 GB 13.1 GB
Too big Get file →
—10.7 GB 14.5 GB
Too big Get file →

What GPU do you need for Vicuna 13B v1.3?

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: the best quant that fits is the main file (7.9 GB file, about 15.1 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (10.7 GB file, about 17.9 GB in use).

Which Vicuna 13B v1.3 quant should you choose?

If memory is tight, the smallest file is the first one in the table at 7.4 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

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

Source

Quantized bygotzmann
FamilyVicuna
Downloads (HF)38
Last updated2023-10-23

Frequently asked questions about Vicuna 13B v1.3

How much VRAM does Vicuna 13B v1.3 need?

About 16.2 GB at its main file with an 8K context window. That is the 9.0 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 Vicuna 13B v1.3 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 14.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Vicuna 13B v1.3 GGUF?

It depends on the quant: file is 7.4 GB, file is 7.9 GB, file is 9.0 GB, file is 9.2 GB, file is 10.7 GB.

What context length does Vicuna 13B v1.3 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 Vicuna 13B v1.3 GGUF?

The files are on Hugging Face in the gotzmann/Vicuna-13B-v1.3-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 from gotzmann

All by gotzmann →

More Vicuna models

All Vicuna →

Other medium models

All medium models →