BI

Bielik

BielikGGUF by CradUpdated 2024-04-13
Download on Hugging Face
Parameters7.24B
Context4K
Layers32
Architecturellama
Smallest quant1.6 GB
Quick answer

Bielik needs about 3.6 GB of memory at IQ2_XXS (a 2.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 6 quants, from 1.6 GB (IQ1_S) to 3.2 GB (Q3_K_S).

Bielik is a 7.24B-parameter Bielik model in GGUF format, quantized by Crad. Its trained context length is 4K tokens. The repository has 6 quant files, from 1.6 GB (IQ1_S) to 3.2 GB (Q3_K_S).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.6 GB 2.6 GB
Fits Get file →
IQ1_M1.8 GB 2.8 GB
Fits Get file →
IQ2_XXS2.0 GB 3.0 GB
Fits Get file →
IQ3_XXS2.8 GB 3.9 GB
Fits Get file →
IQ3_XS3.0 GB 4.1 GB
Fits Get file →
Q3_K_S3.2 GB 4.2 GB
Fits Get file →

What GPU do you need for Bielik?

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: the best quant that fits is IQ2_XXS (2.0 GB file, about 3.6 GB in use).
  • 6 GB VRAM: the best quant that fits is Q3_K_S (3.2 GB file, about 4.7 GB in use).

Which Bielik quant should you choose?

IQ2_XXS (2.0 GB) is the middle option in this repository. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

If memory is tight, the smallest file is IQ1_S at 1.6 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

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 byCrad
FamilyBielik
Downloads (HF)48
Last updated2024-04-13

Frequently asked questions about Bielik

How much VRAM does Bielik need?

About 3.6 GB at IQ2_XXS with an 8K context window. That is the 2.0 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 Bielik on an 8 GB GPU?

Yes, with Q3_K_S: the 3.2 GB file needs about 4.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Bielik GGUF?

It depends on the quant: IQ1_S is 1.6 GB, IQ1_M is 1.8 GB, IQ2_XXS is 2.0 GB, IQ3_XXS is 2.8 GB, IQ3_XS is 3.0 GB, Q3_K_S is 3.2 GB.

What context length does Bielik 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 Bielik GGUF?

The files are on Hugging Face in the Crad/Bielik-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 Bielik 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.

Similar models

Browse all →

More Bielik models

All Bielik →

Other small models

All small models →