LO

loras wan

LorasGGUF by rgomezs2010Updated 2026-02-16
Download on Hugging Face
Parameters14.3B
Context—
Layers—
Architecturewan
Smallest quant15.4 GB
Quick answer

loras wan needs about 17.8 GB of memory at its main file (a 15.4 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 8 quants, from 15.4 GB to 15.4 GB.

14.3B parameter Loras WAN model

Loras WAN is a 14.3 billion parameter model built on the WAN architecture. It is available in GGUF format with a file size of 15.41 GB. The model requires approximately 17.8 GB of VRAM at an 8 k context length.

Good at

  • Large language modeling
  • Contextual text generation
  • High‑capacity reasoning

Limits

  • No context length specified
  • Memory requirement high for 8 k context
  • License not provided

Best for

  • Research prototyping
  • Fine‑tuning large language tasks
  • Exploratory AI experiments

Who it’s for. Researchers and developers who need a large‑parameter WAN model for experimentation. The model is suitable for those with access to high‑memory GPUs and no strict licensing constraints.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—15.4 GB 17.8 GB
Too big Get file →
—15.4 GB 17.8 GB
Too big Get file →
—15.4 GB 17.8 GB
Too big Get file →
—15.4 GB 17.8 GB
Too big Get file →
—15.4 GB 17.8 GB
Too big Get file →
—15.4 GB 17.8 GB
Too big Get file →
—15.4 GB 17.8 GB
Too big Get file →
—15.4 GB 17.8 GB
Too big Get file →

The only available GGUF file is 15.41 GB and estimates 17.8 GB of VRAM at 8 k context. If you have 20 GB or more VRAM, the model can run unquantized. No other quantized variants are listed, so memory budget must match the unquantized size.

What GPU do you need for loras wan?

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: 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 (15.4 GB file, about 17.8 GB in use).

Which loras wan quant should you choose?

If memory is tight, the smallest file is the first one in the table at 15.4 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
Parameters14.3B

Source

Quantized byrgomezs2010
FamilyLoras
Downloads (HF)4,237
Last updated2026-02-16

Frequently asked questions about loras wan

How much VRAM does loras wan need?

About 17.8 GB at its main file with an 8K context window. That is the 15.4 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 loras wan on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 17.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of loras wan GGUF?

It depends on the quant: file is 15.4 GB, file is 15.4 GB, file is 15.4 GB, file is 15.4 GB, file is 15.4 GB, file is 15.4 GB and 2 more.

Where can I download loras wan GGUF?

The files are on Hugging Face in the rgomezs2010/loras_wan repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run Loras WAN on 8 GB VRAM?

No. The model requires approximately 17.8 GB of VRAM at 8 k context, so 8 GB is insufficient.

What is the context length supported by Loras WAN?

The context length is not specified in the provided data.

Is there a license for using Loras WAN?

No license information is provided in the facts.

Similar models

Browse all →

More Loras models

All Loras →

Other medium models

All medium models →