AN

AnFeng

AnfengGGUF by Cran-MayUpdated 2024-03-09
Download on Hugging Face
Parameters7.72B
Context8K
Layers32
Architecturellama
Smallest quant4.8 GB
Quick answer

AnFeng needs about 18.5 GB of memory at its main file (a 13.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 3 quants, from 4.8 GB to 20.7 GB.

AnFeng is a 7.72B-parameter Anfeng model in GGUF format, quantized by Cran-May. Its trained context length is 8K tokens. The repository has 3 quant files, from 4.8 GB to 20.7 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—4.8 GB 9.6 GB
Too big Get file →
—13.7 GB 18.5 GB
Too big Get file →
—20.7 GB 25.5 GB
Too big Get file →

What GPU do you need for AnFeng?

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: the best quant that fits is the main file (4.8 GB file, about 9.6 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (4.8 GB file, about 9.6 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (13.7 GB file, about 18.5 GB in use).
  • 32 GB VRAM: the best quant that fits is the main file (20.7 GB file, about 25.5 GB in use).

Which AnFeng quant should you choose?

If memory is tight, the smallest file is the first one in the table at 4.8 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
Parameters7.72B
Layers32
Trained context8,192 tokens
KV cache (fp16)512 KB per token

Source

Quantized byCran-May
FamilyAnfeng
RepositoryCran-May/AnFeng
Downloads (HF)55
Last updated2024-03-09

Frequently asked questions about AnFeng

How much VRAM does AnFeng need?

About 18.5 GB at its main file with an 8K context window. That is the 13.7 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 AnFeng on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of AnFeng GGUF?

It depends on the quant: file is 4.8 GB, file is 13.7 GB, file is 20.7 GB.

What context length does AnFeng support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 4.3 GB at 8K and 4.3 GB at 8K.

Where can I download AnFeng GGUF?

The files are on Hugging Face in the Cran-May/AnFeng 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 Cran-May

All by Cran-May →

More Anfeng models

All Anfeng →

Other small models

All small models →