DA

DaringMaid 20B

DaringmaidGGUF by KootenUpdated 2024-01-19
Download on Hugging Face
Parameters20B
Context4K
Layers62
Architecturellama
Smallest quant5.4 GB
Quick answer

DaringMaid 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 5 quants, from 5.4 GB (IQ2_XXS) to 14.2 GB (Q5_K_M).

DaringMaid 20B is a 20B-parameter Daringmaid model in GGUF format, quantized by Kooten. Its trained context length is 4K tokens. The repository has 5 quant files, from 5.4 GB (IQ2_XXS) to 14.2 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_XXS5.4 GB 11.1 GB
Too big Get file →
IQ2_XS5.9 GB 11.6 GB
Too big Get file →
Q3_K_M9.7 GB 15.4 GB
Too big Get file →
Q4_K_M12.0 GB 17.7 GB
Too big Get file →
Q5_K_M14.2 GB 19.9 GB
Too big Get file →

What GPU do you need for DaringMaid 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).

Which DaringMaid 20B quant should you choose?

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

If memory is tight, the smallest file is IQ2_XXS at 5.4 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

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 byKooten
Downloads (HF)199
Last updated2024-01-19

Frequently asked questions about DaringMaid 20B

How much VRAM does DaringMaid 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 DaringMaid 20B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 16.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of DaringMaid 20B GGUF?

It depends on the quant: IQ2_XXS is 5.4 GB, IQ2_XS is 5.9 GB, Q3_K_M is 9.7 GB, Q4_K_M is 12.0 GB, Q5_K_M is 14.2 GB.

What context length does DaringMaid 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 DaringMaid 20B GGUF?

The files are on Hugging Face in the Kooten/DaringMaid-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 DaringMaid 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 Kooten

All by Kooten →

More Daringmaid models

All Daringmaid →

Other medium models

All medium models →