UP

Upscalers

UpscalersGGUF by Isi99999Updated 2025-07-26
Download on Hugging Face
Parameters11.9B
Context—
Layers—
Architectureflux
Smallest quant9.8 GB
Quick answer

Upscalers needs about 14.7 GB of memory at Q8_0 (a 12.7 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 4 quants, from 9.8 GB (Q6_K) to 12.7 GB (Q8_0).

Flux-based Upscalers model for image enhancement

Upscalers is a 11.9B parameter flux architecture model. It is released under the apache-2.0 license and is available in several GGUF quantizations. The model focuses on upscaling tasks.

Good at

  • Image upscaling
  • High resolution enhancement
  • Pixel level detail preservation

Limits

  • No vision support beyond upscaling
  • Requires 8k context for full performance
  • Large VRAM needed for higher quantizations

Best for

  • Enhancing low‑res photos
  • Restoring old images
  • Preparing assets for high‑resolution displays

Who it’s for. Developers and researchers needing a dedicated upscaling model. The model is suitable for integration into image processing pipelines where high‑quality detail is required.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q6_K9.8 GB 11.5 GB
Too big Get file →
Q8_012.7 GB 14.7 GB
Too big Get file →
Q8_012.7 GB 14.7 GB
Too big Get file →
Q8_012.7 GB 14.8 GB
Too big Get file →

For 8 GB VRAM, use Q6_K (9.85 GB file, ~11.5 GB memory at 8k context). For 12 GB VRAM, Q8_0 variants (12.71–12.73 GB file, ~14.7–14.8 GB memory) are suitable. Memory estimates are approximate.

What GPU do you need for Upscalers?

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: the best quant that fits is Q6_K (9.8 GB file, about 11.5 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (12.7 GB file, about 14.8 GB in use).

Which Upscalers quant should you choose?

Q8_0 (12.7 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.

If memory is tight, the smallest file is Q6_K at 9.8 GB, with the quality trade-offs that come with fewer bits. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureflux
Parameters11.9B

Source

Quantized byIsi99999
FamilyUpscalers
Licenseapache-2.0
Downloads (HF)770
Last updated2025-07-26

Frequently asked questions about Upscalers

How much VRAM does Upscalers need?

About 14.7 GB at Q8_0 with an 8K context window. That is the 12.7 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 Upscalers on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Upscalers GGUF?

It depends on the quant: Q6_K is 9.8 GB, Q8_0 is 12.7 GB, Q8_0 is 12.7 GB, Q8_0 is 12.7 GB.

Where can I download Upscalers GGUF?

The files are on Hugging Face in the Isi99999/Upscalers repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Upscalers 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.

Can I run Upscalers on 8 GB VRAM?

Yes, the Q6_K quantization requires about 11.5 GB memory at 8k context, which is close to 8 GB VRAM but may need off‑load or lower context.

Does Upscalers support other languages?

No, the model is not trained for language tasks.

Similar models

Browse all →

More from Isi99999

All by Isi99999 →

Other medium models

All medium models →