WI

WindyLLM kor jpn eng Q8 0

WindyllmGGUF by tklohjUpdated 2024-07-28
Download on Hugging Face
Parameters7.59B
Context8K
Layers30
Architecturellama
Smallest quant8.1 GB
Quick answer

WindyLLM kor jpn eng Q8 0 needs about 9.6 GB of memory at Q8_0 (a 8.1 GB file) with an 8K context window, so it fits on a 12 GB GPU.

WindyLLM kor jpn eng Q8 0 is a 7.59B-parameter Windyllm model in GGUF format, quantized by tklohj. Its trained context length is 8K tokens. The repository has 1 quant file, from 8.1 GB (Q8_0) to 8.1 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_08.1 GB 9.6 GB
Too big Get file →

What GPU do you need for WindyLLM kor jpn eng Q8 0?

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 Q8_0 (8.1 GB file, about 9.6 GB in use).

Which WindyLLM kor jpn eng Q8 0 quant should you choose?

Q8_0 (8.1 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters7.59B
Layers30
Trained context8,192 tokens
KV cache (fp16)120 KB per token

Source

Quantized bytklohj
FamilyWindyllm
Downloads (HF)13
Last updated2024-07-28

Frequently asked questions about WindyLLM kor jpn eng Q8 0

How much VRAM does WindyLLM kor jpn eng Q8 0 need?

About 9.6 GB at Q8_0 with an 8K context window. That is the 8.1 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 WindyLLM kor jpn eng Q8 0 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of WindyLLM kor jpn eng Q8 0 GGUF?

It depends on the quant: Q8_0 is 8.1 GB.

What context length does WindyLLM kor jpn eng Q8 0 support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.0 GB at 8K and 1.0 GB at 8K.

Where can I download WindyLLM kor jpn eng Q8 0 GGUF?

The files are on Hugging Face in the tklohj/WindyLLM_kor_jpn_eng-Q8_0-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 tklohj

All by tklohj →

More Windyllm models

All Windyllm →

Other small models

All small models →