VA

vae

VaeGGUF by asdasdasd1234567890Updated 2026-04-13
Download on Hugging Face
Parameters127M
Context—
Layers—
Architecturepig
Smallest quant0.3 GB
Quick answer

vae needs about 0.8 GB of memory at F16 (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU.

vae is a 127M-parameter Vae model in GGUF format, quantized by asdasdasd1234567890. The repository has 1 quant file, from 0.3 GB (F16) to 0.3 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F160.3 GB 0.8 GB
Fits Get file →

What GPU do you need for vae?

These figures add the file size, an fp16 KV cache at an 8K context window 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: the best quant that fits is F16 (0.3 GB file, about 0.8 GB in use).

Which vae quant should you choose?

F16 (0.3 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturepig
Parameters127M

Source

FamilyVae
Downloads (HF)9
Last updated2026-04-13

Frequently asked questions about vae

How much VRAM does vae need?

About 0.8 GB at F16 with an 8K context window. That is the 0.3 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 vae on an 8 GB GPU?

Yes, with F16: the 0.3 GB file needs about 0.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of vae GGUF?

It depends on the quant: F16 is 0.3 GB.

Where can I download vae GGUF?

The files are on Hugging Face in the asdasdasd1234567890/vae 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 asdasdasd1234567890

All by asdasdasd1234567890 →

More Vae models

All Vae →

Other tiny models

All tiny models →