SA

Sakura 1B8 Alignment

SakuraGGUF by TransWithAIUpdated 2024-03-23
Download on Hugging Face
Parameters1.84B
Context32K
Layers24
Architectureqwen2
Smallest quant3.7 GB
Quick answer

Sakura 1B8 Alignment needs about 5.8 GB of memory at its main file (a 3.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

Sakura 1B8 Alignment is a 1.84B-parameter Sakura model in GGUF format, quantized by TransWithAI. Its trained context length is 32K tokens. The repository has 1 quant file, from 3.7 GB to 3.7 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—3.7 GB 5.8 GB
Fits Get file →

What GPU do you need for Sakura 1B8 Alignment?

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 the main file (3.7 GB file, about 5.8 GB in use).

Specifications

Architecture from the GGUF header

Architectureqwen2
Parameters1.84B
Layers24
Trained context32,768 tokens
KV cache (fp16)192 KB per token

Source

Quantized byTransWithAI
FamilySakura
Licenseapache-2.0
Downloads (HF)38
Last updated2024-03-23

Frequently asked questions about Sakura 1B8 Alignment

How much VRAM does Sakura 1B8 Alignment need?

About 5.8 GB at its main file with an 8K context window. That is the 3.7 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 Sakura 1B8 Alignment on an 8 GB GPU?

Yes, with the smaller files: the 3.7 GB file needs about 5.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Sakura 1B8 Alignment GGUF?

It depends on the quant: file is 3.7 GB.

What context length does Sakura 1B8 Alignment support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.

Where can I download Sakura 1B8 Alignment GGUF?

The files are on Hugging Face in the TransWithAI/Sakura-1B8-Alignment-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 Sakura 1B8 Alignment 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 TransWithAI

All by TransWithAI →

More Sakura models

All Sakura →

Other tiny models

All tiny models →