WI

wizard-vicuna-13b-uncensored-superhot-8k.ggmlv3.q4_K_M.bin

WizardGGUF by JohanARUpdated 2023-09-23
Download on Hugging Face
Parameters13B
Context8K
Layers40
Architecturellama
Smallest quant7.9 GB
Quick answer

wizard-vicuna-13b-uncensored-superhot-8k.ggmlv3.q4_K_M.bin needs about 15.1 GB of memory at Q4_K_M (a 7.9 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 2 quants, from 7.9 GB (Q4_K_M) to 9.2 GB (Q5_K_M).

wizard-vicuna-13b-uncensored-superhot-8k.ggmlv3.q4_K_M.bin is a 13B-parameter Wizard model in GGUF format, quantized by JohanAR. Its trained context length is 8K tokens. The repository has 2 quant files, from 7.9 GB (Q4_K_M) to 9.2 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M7.9 GB 15.1 GB
Too big Get file →
Q5_K_M9.2 GB 16.4 GB
Too big Get file →

What GPU do you need for wizard-vicuna-13b-uncensored-superhot-8k.ggmlv3.q4_K_M.bin?

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 Q4_K_M (7.9 GB file, about 15.1 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_K_M (9.2 GB file, about 16.4 GB in use).

Which wizard-vicuna-13b-uncensored-superhot-8k.ggmlv3.q4_K_M.bin quant should you choose?

Q4_K_M is the usual starting point for wizard-vicuna-13b-uncensored-superhot-8k.ggmlv3.q4_K_M.bin: it balances file size and quality well. Here it is a 7.9 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters13B
Layers40
Trained context8,196 tokens
KV cache (fp16)800 KB per token

Source

Quantized byJohanAR
FamilyWizard
Licenseother
Downloads (HF)61
Last updated2023-09-23

Frequently asked questions about wizard-vicuna-13b-uncensored-superhot-8k.ggmlv3.q4_K_M.bin

How much VRAM does wizard-vicuna-13b-uncensored-superhot-8k.ggmlv3.q4_K_M.bin need?

About 15.1 GB at Q4_K_M with an 8K context window. That is the 7.9 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 wizard-vicuna-13b-uncensored-superhot-8k.ggmlv3.q4_K_M.bin on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of wizard-vicuna-13b-uncensored-superhot-8k.ggmlv3.q4_K_M.bin GGUF?

It depends on the quant: Q4_K_M is 7.9 GB, Q5_K_M is 9.2 GB.

What context length does wizard-vicuna-13b-uncensored-superhot-8k.ggmlv3.q4_K_M.bin support?

The GGUF header lists a trained context length of 8,196 tokens (8K). The KV cache grows with the context you use: about 6.7 GB at 8K and 6.7 GB at 8K.

Where can I download wizard-vicuna-13b-uncensored-superhot-8k.ggmlv3.q4_K_M.bin GGUF?

The files are on Hugging Face in the JohanAR/Wizard-Vicuna-13B-Uncensored-SuperHOT-8K-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 wizard-vicuna-13b-uncensored-superhot-8k.ggmlv3.q4_K_M.bin use?

Hugging Face lists the license as other. 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 Wizard models

All Wizard →

Other medium models

All medium models →