HE

Hestia 20b

HestiaGGUF by athirdpathUpdated 2023-11-27
Download on Hugging Face
Parameters20B
Context4K
Layers62
Architecturellama
Smallest quant12.0 GB
Quick answer

Hestia 20b needs about 22.9 GB of memory at Q4_K_M (a 12.0 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 4 quants, from 12.0 GB (Q4_K_M) to 40.0 GB.

Hestia 20b is a 20B-parameter Hestia model in GGUF format, quantized by athirdpath. Its trained context length is 4K tokens. The repository has 4 quant files, from 12.0 GB (Q4_K_M) to 40.0 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M12.0 GB 17.7 GB
Too big Get file →
Q5_K_M14.2 GB 19.9 GB
Too big Get file →
Q8_021.2 GB 26.9 GB
Too big Get file →
—40.0 GB 45.7 GB
Too big Get file →

What GPU do you need for Hestia 20b?

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 Q4_K_M (12.0 GB file, about 22.9 GB in use).
  • 32 GB VRAM: the best quant that fits is Q5_K_M (14.2 GB file, about 25.1 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (21.2 GB file, about 32.1 GB in use).

Which Hestia 20b quant should you choose?

Q4_K_M is the usual starting point for Hestia 20b: it balances file size and quality well. Here it is a 12.0 GB file.

The Q8_0 file is 21.2 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters20B
Layers62
Trained context4,096 tokens
KV cache (fp16)1240 KB per token

Source

Quantized byathirdpath
FamilyHestia
Downloads (HF)11
Last updated2023-11-27

Frequently asked questions about Hestia 20b

How much VRAM does Hestia 20b need?

About 22.9 GB at Q4_K_M with an 8K context window. That is the 12.0 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 Hestia 20b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 22.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Hestia 20b GGUF?

It depends on the quant: Q4_K_M is 12.0 GB, Q5_K_M is 14.2 GB, Q8_0 is 21.2 GB, file is 40.0 GB.

What context length does Hestia 20b support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 10.4 GB at 8K and 5.2 GB at 4K.

Where can I download Hestia 20b GGUF?

The files are on Hugging Face in the athirdpath/Hestia-20b-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 Hestia 20b use?

Hugging Face lists the license as cc-by-nc-4.0. 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 athirdpath

All by athirdpath →

More Hestia models

All Hestia →

Other medium models

All medium models →