KU

finch

KunoichiGGUF by antiven0mUpdated 2024-02-11
Download on Hugging Face
Parameters7.24B
Context32K
Layers32
Architecturellama
Smallest quant3.5 GB
Quick answer

finch needs about 6.7 GB of memory at Q5_K (a 5.1 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 6 quants, from 3.5 GB (Q3_K) to 14.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

finch is a 7.24B-parameter Kunoichi model in GGUF format, quantized by antiven0m. Its trained context length is 32K tokens. The repository has 6 quant files, from 3.5 GB (Q3_K) to 14.5 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K3.5 GB 5.1 GB
Fits Get file →
Q4_K4.4 GB 5.9 GB
Fits Get file →
Q5_K5.1 GB 6.7 GB
Fits Get file →
Q6_K5.9 GB 7.5 GB
Tight Get file →
Q8_07.7 GB 9.3 GB
Too big Get file →
F1614.5 GB 16.1 GB
Too big Get file →

What GPU do you need for finch?

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 Q4_K (4.4 GB file, about 5.9 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).
  • 16 GB VRAM: the best quant that fits is Q8_0 (7.7 GB file, about 9.3 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (14.5 GB file, about 16.1 GB in use).

Which finch quant should you choose?

Q5_K (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 Q3_K at 3.5 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 context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byantiven0m
FamilyKunoichi
Downloads (HF)96
Last updated2024-02-11

Frequently asked questions about finch

How much VRAM does finch need?

About 6.7 GB at Q5_K 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 finch 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 finch GGUF?

It depends on the quant: Q3_K is 3.5 GB, Q4_K is 4.4 GB, Q5_K is 5.1 GB, Q6_K is 5.9 GB, Q8_0 is 7.7 GB, F16 is 14.5 GB.

What context length does finch support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download finch GGUF?

The files are on Hugging Face in the antiven0m/finch-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 finch 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.

Other GGUFs of Kunoichi-DPO-v2-7B

Similar models

Browse all →

More from antiven0m

All by antiven0m →

More Kunoichi models

All Kunoichi →

Other small models

All small models →