SA

Sabaki Preview

SabakiGGUF by Local-Axiom-AIUpdated 2026-10-19
Download on Hugging Face
Parameters222M
Context16K
Layers16
Architecturekurokiba
Smallest quant0.4 GB
Quick answer

Sabaki Preview needs about 1.3 GB of memory at F16 (a 0.4 GB file) with an 8K context window, so it fits on a 4 GB GPU.

Sabaki Preview is a 222M-parameter Sabaki model in GGUF format, quantized by Local-Axiom-AI. Its trained context length is 16K tokens. The repository has 1 quant file, from 0.4 GB (F16) to 0.4 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F160.4 GB 1.3 GB
Fits Get file →

What GPU do you need for Sabaki Preview?

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 F16 (0.4 GB file, about 1.3 GB in use).

Which Sabaki Preview quant should you choose?

F16 (0.4 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturekurokiba
Parameters222M (approximate, mixture of experts)
Layers16
Trained context16,384 tokens
KV cache (fp16)48 KB per token

Source

Quantized byLocal-Axiom-AI
FamilySabaki
Downloads (HF)88
Last updated2026-10-19

Frequently asked questions about Sabaki Preview

How much VRAM does Sabaki Preview need?

About 1.3 GB at F16 with an 8K context window. That is the 0.4 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 Sabaki Preview on an 8 GB GPU?

Yes, with F16: the 0.4 GB file needs about 1.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Sabaki Preview GGUF?

It depends on the quant: F16 is 0.4 GB.

What context length does Sabaki Preview support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 0.4 GB at 8K and 0.8 GB at 16K.

Where can I download Sabaki Preview GGUF?

The files are on Hugging Face in the Local-Axiom-AI/Sabaki-Preview repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Sabaki Preview 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 from Local-Axiom-AI

All by Local-Axiom-AI →

More Sabaki models

All Sabaki →

Other tiny models

All tiny models →