EX

extrarepo

ExtrarepoGGUF by jeikuUpdated 2024-03-18
Download on Hugging Face
Parameters7.24B
Context32K
Layers40
Architecturellama
Smallest quant3.7 GB
Quick answer

extrarepo needs about 6.2 GB of memory at Q4_K (a 4.4 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 7 quants, from 3.7 GB (IQ3_XS) to 5.9 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

extrarepo is a 7.24B-parameter Extrarepo model in GGUF format, quantized by jeiku. Its trained context length is 32K tokens. The repository has 7 quant files, from 3.7 GB (IQ3_XS) to 5.9 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ3_XS3.7 GB 5.6 GB
Fits Get file →
Q4_K4.4 GB 6.2 GB
Fits Get file →
Q4_K4.4 GB 6.2 GB
Fits Get file →
Q4_K4.4 GB 6.2 GB
Fits Get file →
Q4_K4.4 GB 6.2 GB
Fits Get file →
Q5_K5.1 GB 7.0 GB
Fits Get file →
Q6_K5.9 GB 7.8 GB
Tight Get file →

What GPU do you need for extrarepo?

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 IQ3_XS (3.7 GB file, about 5.6 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (5.9 GB file, about 7.8 GB in use).

Which extrarepo quant should you choose?

Q4_K (4.4 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is IQ3_XS at 3.7 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
Layers40
Trained context32,768 tokens
KV cache (fp16)160 KB per token

Source

Quantized byjeiku
FamilyExtrarepo
Repositoryjeiku/extrarepo
Downloads (HF)28
Last updated2024-03-18

Frequently asked questions about extrarepo

How much VRAM does extrarepo need?

About 6.2 GB at Q4_K with an 8K context window. That is the 4.4 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 extrarepo on an 8 GB GPU?

Yes, with Q6_K: the 5.9 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of extrarepo GGUF?

It depends on the quant: IQ3_XS is 3.7 GB, Q4_K is 4.4 GB, Q4_K is 4.4 GB, Q4_K is 4.4 GB, Q4_K is 4.4 GB, Q5_K is 5.1 GB and 1 more.

What context length does extrarepo support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download extrarepo GGUF?

The files are on Hugging Face in the jeiku/extrarepo 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 jeiku

All by jeiku →

Other small models

All small models →