SP

SparkVSR

SparkvsrGGUF by smthemUpdated 2026-03-25
Download on Hugging Face
Parameters5.57B
Context—
Layers—
Architectureflux
Smallest quant7.9 GB
Quick answer

SparkVSR needs about 9.3 GB of memory at Q8_0 (a 7.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 2 quants, from 7.9 GB (Q8_0) to 7.9 GB (Q8_0).

SparkVSR – a 5.57B flux model in GGUF format

SparkVSR is a 5.57 billion parameter flux model released under the MIT license. It is distributed as a single Q8_0 quantized GGUF file. The model is available from the smthem/SparkVSR-GGUF repository on Hugging Face.

Good at

  • Large context handling
  • High precision inference
  • Flux architecture

Limits

  • No vision support
  • Requires 9.3 GB VRAM at 8k context
  • Single quant available

Best for

  • Research on flux models
  • Benchmarking GGUF quantization
  • Educational demos

Who it’s for. Developers and researchers who need a high‑precision flux model in GGUF format. The model is suitable for those who can allocate sufficient VRAM and are comfortable with a single quantization level.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_07.9 GB 9.3 GB
Too big Get file →
Q8_07.9 GB 9.3 GB
Too big Get file →

The only available quant is Q8_0, with a file size of 7.89 GB and an estimated memory usage of 9.3 GB at 8k context. For systems with 8 GB VRAM, the model will not fit. If larger VRAM is available, Q8_0 can be used directly.

What GPU do you need for SparkVSR?

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 Q8_0 (7.9 GB file, about 9.3 GB in use).

Which SparkVSR quant should you choose?

Q8_0 (7.9 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureflux
Parameters5.57B

Source

Quantized bysmthem
FamilySparkvsr
Licensemit
Downloads (HF)1,285
Last updated2026-03-25

Frequently asked questions about SparkVSR

How much VRAM does SparkVSR need?

About 9.3 GB at Q8_0 with an 8K context window. That is the 7.9 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 SparkVSR on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of SparkVSR GGUF?

It depends on the quant: Q8_0 is 7.9 GB, Q8_0 is 7.9 GB.

Where can I download SparkVSR GGUF?

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

What license does SparkVSR use?

Hugging Face lists the license as mit. 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 SparkVSR on 8 GB VRAM?

No, the model requires 9.3 GB VRAM at 8k context, so 8 GB is insufficient.

Is SparkVSR a mixture of experts?

No, SparkVSR is not a mixture of experts.

Similar models

Browse all →

More from smthem

All by smthem →

More Sparkvsr models

All Sparkvsr →

Other small models

All small models →