BA

base wan21

BaseGGUF by JustAnotherCibrarianUpdated 2025-09-03
Download on Hugging Face
Parameters16.4B
Context—
Layers—
Architecturewan
Smallest quant3.1 GB
Quick answer

base wan21 needs about 12.7 GB of memory at its main file (a 10.9 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 6 quants, from 3.1 GB to 12.0 GB.

base wan21 is a 16.4B-parameter Base model in GGUF format, quantized by JustAnotherCibrarian. The repository has 6 quant files, from 3.1 GB to 12.0 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—3.1 GB 3.9 GB
Fits Get file →
—10.9 GB 12.7 GB
Too big Get file →
—10.9 GB 12.7 GB
Too big Get file →
—11.4 GB 13.3 GB
Too big Get file →
—12.0 GB 13.9 GB
Too big Get file →
—12.0 GB 13.9 GB
Too big Get file →

What GPU do you need for base wan21?

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 the main file (3.1 GB file, about 3.9 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (3.1 GB file, about 3.9 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (3.1 GB file, about 3.9 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (3.1 GB file, about 3.9 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (12.0 GB file, about 13.9 GB in use).

Which base wan21 quant should you choose?

If memory is tight, the smallest file is the first one in the table at 3.1 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturewan
Parameters16.4B

Source

FamilyBase
Downloads (HF)0
Last updated2025-09-03

Frequently asked questions about base wan21

How much VRAM does base wan21 need?

About 12.7 GB at its main file with an 8K context window. That is the 10.9 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 base wan21 on an 8 GB GPU?

Yes, with the smaller files: the 3.1 GB file needs about 3.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of base wan21 GGUF?

It depends on the quant: file is 3.1 GB, file is 10.9 GB, file is 10.9 GB, file is 11.4 GB, file is 12.0 GB, file is 12.0 GB.

Where can I download base wan21 GGUF?

The files are on Hugging Face in the JustAnotherCibrarian/base_wan21 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 JustAnotherCibrarian

All by JustAnotherCibrarian →

More Base models

All Base →

Other medium models

All medium models →