JA

Japanese TextGen Kage v0.1 2x7B

JapaneseGGUF by dddumpUpdated 2024-05-19
Download on Hugging Face
Parameters12.9B
Context32K
Layers32
Architecturellama
Smallest quant6.9 GB
Quick answer

Japanese TextGen Kage v0.1 2x7B needs about 8.5 GB of memory at IQ4_XS (a 6.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Japanese TextGen Kage v0.1 2x7B is a 12.9B-parameter Japanese model in GGUF format, quantized by dddump. Its trained context length is 32K tokens. The repository has 1 quant file, from 6.9 GB (IQ4_XS) to 6.9 GB (IQ4_XS).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ4_XS6.9 GB 8.5 GB
Too big Get file →

What GPU do you need for Japanese TextGen Kage v0.1 2x7B?

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: the best quant that fits is IQ4_XS (6.9 GB file, about 8.5 GB in use).

Which Japanese TextGen Kage v0.1 2x7B quant should you choose?

IQ4_XS (6.9 GB) is the middle option in this repository. 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

Architecturellama
Parameters12.9B (approximate, mixture of experts)
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized bydddump
FamilyJapanese
Downloads (HF)57
Last updated2024-05-19

Frequently asked questions about Japanese TextGen Kage v0.1 2x7B

How much VRAM does Japanese TextGen Kage v0.1 2x7B need?

About 8.5 GB at IQ4_XS with an 8K context window. That is the 6.9 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 Japanese TextGen Kage v0.1 2x7B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Japanese TextGen Kage v0.1 2x7B GGUF?

It depends on the quant: IQ4_XS is 6.9 GB.

What context length does Japanese TextGen Kage v0.1 2x7B support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download Japanese TextGen Kage v0.1 2x7B GGUF?

The files are on Hugging Face in the dddump/Japanese-TextGen-Kage-v0.1-2x7B-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from dddump

All by dddump →

More Japanese models

All Japanese →

Other medium models

All medium models →