AE

Aeonis 20b

AeonisGGUF by athirdpathUpdated 2024-09-04
Download on Hugging Face
Parameters20.4B
Context1000K
Layers70
Architecturellama
Smallest quant12.4 GB
Quick answer

Aeonis 20b needs about 15.2 GB of memory at Q4_K_M (a 12.4 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 4 quants, from 12.4 GB (Q4_K_M) to 21.7 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 9.4 GB.

Aeonis 20b is a 20.4B-parameter Aeonis model in GGUF format, quantized by athirdpath. Its trained context length is 1000K tokens. The repository has 4 quant files, from 12.4 GB (Q4_K_M) to 21.7 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M12.4 GB 15.2 GB
Too big Get file →
Q5_K_M14.5 GB 17.3 GB
Too big Get file →
Q6_K_M16.8 GB 19.6 GB
Too big Get file →
—21.7 GB 24.6 GB
Too big Get file →

What GPU do you need for Aeonis 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: the best quant that fits is Q4_K_M (12.4 GB file, about 15.2 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K_M (16.8 GB file, about 19.6 GB in use).
  • 32 GB VRAM: the best quant that fits is the main file (21.7 GB file, about 24.6 GB in use).

Which Aeonis 20b quant should you choose?

Q4_K_M is the usual starting point for Aeonis 20b: it balances file size and quality well. Here it is a 12.4 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters20.4B
Layers70
Trained context1,024,000 tokens
KV cache (fp16)280 KB per token

Source

Quantized byathirdpath
FamilyAeonis
Licenseapache-2.0
Downloads (HF)37
Last updated2024-09-04

Frequently asked questions about Aeonis 20b

How much VRAM does Aeonis 20b need?

About 15.2 GB at Q4_K_M with an 8K context window. That is the 12.4 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 Aeonis 20b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Aeonis 20b GGUF?

It depends on the quant: Q4_K_M is 12.4 GB, Q5_K_M is 14.5 GB, Q6_K_M is 16.8 GB, file is 21.7 GB.

What context length does Aeonis 20b support?

The GGUF header lists a trained context length of 1,024,000 tokens (1000K). The KV cache grows with the context you use: about 2.3 GB at 8K and 9.4 GB at 32K.

Where can I download Aeonis 20b GGUF?

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

Hugging Face lists the license as apache-2.0. 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 Aeonis models

All Aeonis →

Other medium models

All medium models →