BE

bekko embedding v1 a25m

BekkoGGUF by hotchpotchUpdated 2026-08-05
Download on Hugging Face
Parameters123M
Context8K
Layers13
Architecturemodern-bert
Smallest quant0.1 GB
Quick answer

bekko embedding v1 a25m needs about 0.9 GB of memory at BF16 (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 0.1 GB (Q8_0) to 0.3 GB (F16).

bekko embedding v1 a25m is a 123M-parameter Bekko model in GGUF format, quantized by hotchpotch. Its trained context length is 8K tokens. The repository has 3 quant files, from 0.1 GB (Q8_0) to 0.3 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_00.1 GB 0.8 GB
Fits Get file →
BF160.3 GB 0.9 GB
Fits Get file →
F160.3 GB 0.9 GB
Fits Get file →

What GPU do you need for bekko embedding v1 a25m?

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 BF16 (0.3 GB file, about 0.9 GB in use).

Which bekko embedding v1 a25m quant should you choose?

BF16 (0.3 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

If memory is tight, the smallest file is Q8_0 at 0.1 GB, with the quality trade-offs that come with fewer bits. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturemodern-bert
Parameters123M
Layers13
Trained context8,192 tokens
KV cache (fp16)20 KB per token

Source

Quantized byhotchpotch
FamilyBekko
Licensemit
Downloads (HF)263
Last updated2026-08-05

Frequently asked questions about bekko embedding v1 a25m

How much VRAM does bekko embedding v1 a25m need?

About 0.9 GB at BF16 with an 8K context window. That is the 0.3 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 bekko embedding v1 a25m on an 8 GB GPU?

Yes, with BF16: the 0.3 GB file needs about 0.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of bekko embedding v1 a25m GGUF?

It depends on the quant: Q8_0 is 0.1 GB, BF16 is 0.3 GB, F16 is 0.3 GB.

What context length does bekko embedding v1 a25m support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.2 GB at 8K.

Where can I download bekko embedding v1 a25m GGUF?

The files are on Hugging Face in the hotchpotch/bekko-embedding-v1-a25m-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 bekko embedding v1 a25m use?

Hugging Face lists the license as mit. 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 bekko-embedding-v1-a25m

Similar models

Browse all →

More from hotchpotch

All by hotchpotch →

More Bekko models

All Bekko →

Other tiny models

All tiny models →