WI

kpok

WizardlmGGUF by 754gegUpdated 2024-04-28
Download on Hugging Face
Parameters141B
Context64K
Layers56
Architecturellama
Smallest quant29.6 GB
Quick answer

kpok needs about 32.0 GB of memory at IQ1_S (a 29.6 GB file) with an 8K context window, so it fits on a 32 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 7.5 GB.

kpok is a 141B-parameter Wizardlm model in GGUF format, quantized by 754geg. Its trained context length is 64K tokens. The repository has 1 quant file, from 29.6 GB (IQ1_S) to 29.6 GB (IQ1_S).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S29.6 GB 32.0 GB
Too big Get file →

What GPU do you need for kpok?

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: no quant fits at an 8K context.
  • 32 GB VRAM: the best quant that fits is IQ1_S (29.6 GB file, about 32.0 GB in use).

Which kpok quant should you choose?

IQ1_S (29.6 GB) is the middle option in this repository. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters141B (approximate, mixture of experts)
Layers56
Trained context65,536 tokens
KV cache (fp16)224 KB per token

Source

Quantized by754geg
FamilyWizardlm
Repository754geg/kpok
Licenseapache-2.0
Downloads (HF)16
Last updated2024-04-28

Frequently asked questions about kpok

How much VRAM does kpok need?

About 32.0 GB at IQ1_S with an 8K context window. That is the 29.6 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 kpok on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 32.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of kpok GGUF?

It depends on the quant: IQ1_S is 29.6 GB.

What context length does kpok support?

The GGUF header lists a trained context length of 65,536 tokens (64K). The KV cache grows with the context you use: about 1.9 GB at 8K and 7.5 GB at 32K.

Where can I download kpok GGUF?

The files are on Hugging Face in the 754geg/kpok repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does kpok 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 WizardLM-2-8x22B

Similar models

Browse all →

More Wizardlm models

All Wizardlm →

Other large models

All large models →