SO

Sorbet-25M

SorbetGGUF by CodeSoftUpdated 2026-08-22
Download on Hugging Face
Parameters25M
Context4K
Layers14
Architectureqwen2
Smallest quant0.0 GB
Quick answer

Sorbet-25M needs about 0.6 GB of memory at Q8_K_XL (a 0.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 0.0 GB (Q4_K_XL) to 0.1 GB (F16).

Sorbet-25M is a 25M-parameter Sorbet model in GGUF format, quantized by CodeSoft. Its trained context length is 4K tokens. The repository has 4 quant files, from 0.0 GB (Q4_K_XL) to 0.1 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_XL0.0 GB 0.6 GB
Fits Get file →
Q8_K_XL0.0 GB 0.6 GB
Fits Get file →
BF160.1 GB 0.6 GB
Fits Get file →
F160.1 GB 0.6 GB
Fits Get file →

What GPU do you need for Sorbet-25M?

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 (0.1 GB file, about 0.6 GB in use).

Which Sorbet-25M quant should you choose?

Q8_K_XL (0.0 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

If memory is tight, the smallest file is Q4_K_XL at 0.0 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2
Parameters25M
Layers14
Trained context4,096 tokens
KV cache (fp16)7 KB per token

Source

Quantized byCodeSoft
FamilySorbet
Licenseapache-2.0
Downloads (HF)80
Last updated2026-08-22

Frequently asked questions about Sorbet-25M

How much VRAM does Sorbet-25M need?

About 0.6 GB at Q8_K_XL with an 8K context window. That is the 0.0 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 Sorbet-25M on an 8 GB GPU?

Yes, with BF16: the 0.1 GB file needs about 0.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Sorbet-25M GGUF?

It depends on the quant: Q4_K_XL is 0.0 GB, Q8_K_XL is 0.0 GB, BF16 is 0.1 GB, F16 is 0.1 GB.

What context length does Sorbet-25M support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.0 GB at 4K.

Where can I download Sorbet-25M GGUF?

The files are on Hugging Face in the CodeSoft/sorbet-25m-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 Sorbet-25M use?

Hugging Face lists the license as apache-2.0. 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 from CodeSoft

All by CodeSoft →

More Sorbet models

All Sorbet →

Other tiny models

All tiny models →