YA

EEVE-Korean-Judgment-Transducer-10.8B-v1.0-GGUF

YanoljanextGGUF by SuchaeUpdated 2024-08-01
Download on Hugging Face
Parameters10.8B
Context4K
Layers48
Architecturellama
Smallest quant21.6 GB
Quick answer

EEVE-Korean-Judgment-Transducer-10.8B-v1.0-GGUF needs about 23.7 GB of memory at F16 (a 21.6 GB file) with an 8K context window, so it fits on a 24 GB GPU.

EEVE-Korean-Judgment-Transducer-10.8B-v1.0-GGUF is a 10.8B-parameter Yanoljanext model in GGUF format, quantized by Suchae. Its trained context length is 4K tokens. The repository has 1 quant file, from 21.6 GB (F16) to 21.6 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F1621.6 GB 22.9 GB
Too big Get file →

What GPU do you need for EEVE-Korean-Judgment-Transducer-10.8B-v1.0-GGUF?

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: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is F16 (21.6 GB file, about 23.7 GB in use).

Which EEVE-Korean-Judgment-Transducer-10.8B-v1.0-GGUF quant should you choose?

F16 (21.6 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
Parameters10.8B
Layers48
Trained context4,096 tokens
KV cache (fp16)192 KB per token

Source

Quantized bySuchae
Licenseapache-2.0
Downloads (HF)44
Last updated2024-08-01

Frequently asked questions about EEVE-Korean-Judgment-Transducer-10.8B-v1.0-GGUF

How much VRAM does EEVE-Korean-Judgment-Transducer-10.8B-v1.0-GGUF need?

About 23.7 GB at F16 with an 8K context window. That is the 21.6 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 EEVE-Korean-Judgment-Transducer-10.8B-v1.0-GGUF on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 23.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of EEVE-Korean-Judgment-Transducer-10.8B-v1.0-GGUF GGUF?

It depends on the quant: F16 is 21.6 GB.

What context length does EEVE-Korean-Judgment-Transducer-10.8B-v1.0-GGUF support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.6 GB at 8K and 0.8 GB at 4K.

Where can I download EEVE-Korean-Judgment-Transducer-10.8B-v1.0-GGUF GGUF?

The files are on Hugging Face in the Suchae/EEVE-Korean-Judgment-Transducer-10.8B-v1.0-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 EEVE-Korean-Judgment-Transducer-10.8B-v1.0-GGUF 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.

Other GGUFs of YanoljaNEXT-EEVE-Instruct-10.8B

Similar models

Browse all →

More from Suchae

All by Suchae →

More Yanoljanext models

All Yanoljanext →

Other medium models

All medium models →