KA

karasu translation 2

KarasuGGUF by NilanEUpdated 2024-02-16
Download on Hugging Face
Parameters1.1B
Context2K
Layers22
Architecturellama
Smallest quant2.2 GB
Quick answer

karasu translation 2 needs about 2.9 GB of memory at F16 (a 2.2 GB file) with an 8K context window, so it fits on a 4 GB GPU.

karasu translation 2 is a 1.1B-parameter Karasu model in GGUF format, quantized by NilanE. Its trained context length is 2K tokens. The repository has 1 quant file, from 2.2 GB (F16) to 2.2 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F162.2 GB 2.7 GB
Fits Get file →

What GPU do you need for karasu translation 2?

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 (2.2 GB file, about 2.9 GB in use).

Which karasu translation 2 quant should you choose?

F16 (2.2 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

Architecturellama
Parameters1.1B
Layers22
Trained context2,048 tokens
KV cache (fp16)22 KB per token

Source

Quantized byNilanE
FamilyKarasu
Licenseapache-2.0
Downloads (HF)41
Last updated2024-02-16

Frequently asked questions about karasu translation 2

How much VRAM does karasu translation 2 need?

About 2.9 GB at F16 with an 8K context window. That is the 2.2 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 karasu translation 2 on an 8 GB GPU?

Yes, with F16: the 2.2 GB file needs about 2.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of karasu translation 2 GGUF?

It depends on the quant: F16 is 2.2 GB.

What context length does karasu translation 2 support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.0 GB at 2K.

Where can I download karasu translation 2 GGUF?

The files are on Hugging Face in the NilanE/karasu-translation-2-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 karasu translation 2 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 NilanE

All by NilanE →

More Karasu models

All Karasu →

Other tiny models

All tiny models →