BE

Berghof-ERP-7B

BerghofGGUF by ReadyONUpdated 2024-06-21
Download on Hugging Face
Parameters7.24B
Context4K
Layers32
Architecturellama
Smallest quant3.0 GB
Quick answer

Berghof-ERP-7B needs about 6.7 GB of memory at Q5_K_M (a 5.1 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 5 quants, from 3.0 GB (IQ3_XS) to 7.7 GB (Q8_0).

Berghof-ERP-7B is a 7.24B-parameter Berghof model in GGUF format, quantized by ReadyON. Its trained context length is 4K tokens. The repository has 5 quant files, from 3.0 GB (IQ3_XS) to 7.7 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ3_XS3.0 GB 4.1 GB
Fits Get file →
IQ4_XS3.9 GB 4.9 GB
Fits Get file →
Q5_K_M5.1 GB 6.2 GB
Fits Get file →
Q6_K5.9 GB 7.0 GB
Fits Get file →
Q8_07.7 GB 8.7 GB
Too big Get file →

What GPU do you need for Berghof-ERP-7B?

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: the best quant that fits is IQ4_XS (3.9 GB file, about 5.5 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (5.9 GB file, about 7.5 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.7 GB file, about 9.3 GB in use).

Which Berghof-ERP-7B quant should you choose?

Q5_K_M (5.1 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

If memory is tight, the smallest file is IQ3_XS at 3.0 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters7.24B
Layers32
Trained context4,096 tokens
KV cache (fp16)128 KB per token

Source

Quantized byReadyON
FamilyBerghof
Downloads (HF)74
Last updated2024-06-21

Frequently asked questions about Berghof-ERP-7B

How much VRAM does Berghof-ERP-7B need?

About 6.7 GB at Q5_K_M with an 8K context window. That is the 5.1 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 Berghof-ERP-7B on an 8 GB GPU?

Yes, with Q6_K: the 5.9 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Berghof-ERP-7B GGUF?

It depends on the quant: IQ3_XS is 3.0 GB, IQ4_XS is 3.9 GB, Q5_K_M is 5.1 GB, Q6_K is 5.9 GB, Q8_0 is 7.7 GB.

What context length does Berghof-ERP-7B support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.1 GB at 8K and 0.5 GB at 4K.

Where can I download Berghof-ERP-7B GGUF?

The files are on Hugging Face in the ReadyON/Berghof-ERP-7B-gguf 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 ReadyON

All by ReadyON →

More Berghof models

All Berghof →

Other small models

All small models →