SR

SRPO Refine Quantized v1.0

SrpoGGUF by wikeeyangUpdated 2025-09-23
Download on Hugging Face
Parameters11.9B
Context—
Layers—
Architecture—
Smallest quant7.7 GB
Quick answer

SRPO Refine Quantized v1.0 needs about 9.1 GB of memory at Q4_1 (a 7.7 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 2 quants, from 7.7 GB (Q4_1) to 12.8 GB (Q8_0).

SRPO Refine Quantized v1.0 – 11.9B parameter diffusion model fine‑tuned for clarity

SRPO Refine Quantized v1.0 is a 11.9B parameter diffusion model based on tencent/SRPO. It is quantized to Q4_1 and Q8_0 for efficient inference. The model improves image clarity and compatibility compared to the original SRPO.

Good at

  • High‑resolution image generation
  • Fine‑tuned aesthetic quality
  • Efficient inference with 8‑bit quantization

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • License is other, not open source

Best for

  • Stable diffusion pipelines
  • ComfyUI workflows
  • Low‑VRAM inference

Who it’s for. Users who need a refined version of SRPO with reduced memory footprint. Suitable for artists and developers working with diffusion models on limited hardware.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_17.7 GB 9.1 GB
Too big Get file →
Q8_012.8 GB 14.9 GB
Too big Get file →

For 8GB VRAM, use Q4_1 (file size 7.67 GB, estimated 9.1 GB at 8k context). For 12GB VRAM, Q8_0 (12.84 GB, 14.9 GB at 8k context) offers higher precision. Memory estimates are approximate.

What GPU do you need for SRPO Refine Quantized v1.0?

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 Q4_1 (7.7 GB file, about 9.1 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (12.8 GB file, about 14.9 GB in use).

Which SRPO Refine Quantized v1.0 quant should you choose?

Q4_1 (7.7 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Parameters11.9B

Source

Quantized bywikeeyang
FamilySrpo
Base modeltencent/SRPO
Licenseother
Downloads (HF)1,253
Last updated2025-09-23

Frequently asked questions about SRPO Refine Quantized v1.0

How much VRAM does SRPO Refine Quantized v1.0 need?

About 9.1 GB at Q4_1 with an 8K context window. That is the 7.7 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 SRPO Refine Quantized v1.0 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of SRPO Refine Quantized v1.0 GGUF?

It depends on the quant: Q4_1 is 7.7 GB, Q8_0 is 12.8 GB.

Where can I download SRPO Refine Quantized v1.0 GGUF?

The files are on Hugging Face in the wikeeyang/SRPO-Refine-Quantized-v1.0 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does SRPO Refine Quantized v1.0 use?

Hugging Face lists the license as other. 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 SRPO Refine Quantized v1.0 on 8GB VRAM?

Yes, the Q4_1 quantization requires about 9.1 GB at 8k context, which fits within 8GB VRAM with some overhead.

Does the model support text‑to‑image only?

The model is a diffusion model; it does not include vision or multimodal capabilities.

What license applies to this model?

The model is released under an 'other' license; refer to the license.txt file for details.

Other GGUFs of SRPO

Similar models

Browse all →

More from wikeeyang

All by wikeeyang →

More Srpo models

All Srpo →

Other medium models

All medium models →