SK

Sky T1q4part

SkyGGUF by rakmikUpdated 2025-01-13
Download on Hugging Face
Parameters32.8B
Context32K
Layers64
Architectureqwen2
Smallest quant19.9 GB
Quick answer

Sky T1q4part needs about 22.5 GB of memory at its main file (a 19.9 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

Sky T1q4part is a 32.8B-parameter Sky model in GGUF format, quantized by rakmik. Its trained context length is 32K tokens. The repository has 1 quant file, from 19.9 GB to 19.9 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—19.9 GB (4 parts) 22.5 GB
Too big Get file →

What GPU do you need for Sky T1q4part?

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 the main file (19.9 GB file, about 22.5 GB in use).

Specifications

Architecture from the GGUF header

Architectureqwen2
Parameters32.8B
Layers64
Trained context32,768 tokens
KV cache (fp16)256 KB per token

Source

Quantized byrakmik
FamilySky
Licenseapache-2.0
Downloads (HF)12
Last updated2025-01-13

Frequently asked questions about Sky T1q4part

How much VRAM does Sky T1q4part need?

About 22.5 GB at its main file with an 8K context window. That is the 19.9 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 Sky T1q4part on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 22.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Sky T1q4part GGUF?

It depends on the quant: file is 19.9 GB.

What context length does Sky T1q4part support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.

Where can I download Sky T1q4part GGUF?

The files are on Hugging Face in the rakmik/Sky-T1q4part repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Sky T1q4part 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.

Similar models

Browse all →

More from rakmik

All by rakmik →

More Sky models

All Sky →

Other medium models

All medium models →