TR

SkunkApe 14b

TripleGGUF by SzilviaBUpdated 2024-09-30
Download on Hugging Face
Parameters14.2B
Context8K
Layers64
Architecturellama
Smallest quant30.2 GB
Quick answer

SkunkApe 14b needs about 32.9 GB of memory at Q8_0 (a 30.2 GB file) with an 8K context window, so it fits on a 48 GB GPU.

SkunkApe 14b is a 14.2B-parameter Triple model in GGUF format, quantized by SzilviaB. Its trained context length is 8K tokens. The repository has 1 quant file, from 30.2 GB (Q8_0) to 30.2 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_030.2 GB (4 parts) 32.9 GB
Too big Get file →

What GPU do you need for SkunkApe 14b?

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: no quant fits at an 8K context.
  • 48 GB VRAM: the best quant that fits is Q8_0 (30.2 GB file, about 32.9 GB in use).

Which SkunkApe 14b quant should you choose?

Q8_0 (30.2 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
Parameters14.2B
Layers64
Trained context8,192 tokens
KV cache (fp16)256 KB per token

Source

Quantized bySzilviaB
FamilyTriple
Downloads (HF)16
Last updated2024-09-30

Frequently asked questions about SkunkApe 14b

How much VRAM does SkunkApe 14b need?

About 32.9 GB at Q8_0 with an 8K context window. That is the 30.2 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 SkunkApe 14b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 32.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of SkunkApe 14b GGUF?

It depends on the quant: Q8_0 is 30.2 GB.

What context length does SkunkApe 14b support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 2.1 GB at 8K and 2.1 GB at 8K.

Where can I download SkunkApe 14b GGUF?

The files are on Hugging Face in the SzilviaB/Triple-Skunk-Ape-14B-Q8_0-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of Triple-Skunk-Ape-14B

Similar models

Browse all →

More from SzilviaB

All by SzilviaB →

More Triple models

All Triple →

Other medium models

All medium models →