Downloads · 30 days
28
13% of all-time downloads
SigLIP2-NR-IQA-KonIQ
mlx-community/SigLIP2-NR-IQA-KonIQ
SigLIP2-NR-IQA-KonIQ is a image classification model from mlx-community. Use it when you need a label for an image. It is set up for mlx. The card lists the license as apache-2.0.
No-reference image-quality head on SigLIP2-SO400M for Apple Silicon (MLX). Independent from-paper reproduction of arXiv:2509.17374 — no upstream code/weights were released. The first MLX no-reference IQA head.
All-time downloads
213
Public
Repo size
5.4 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors5.4 MB · 100%
At a glance
- Task
- Image Classification
- Library
- mlx
- License
- apache-2.0
- Access
- Public
- Created
- Jun 6, 2026
- Updated
- Jun 6, 2026
- SHA
- 8349820a
Base models
Model card
From the Hugging Face model README
SigLIP2 NR-IQA (KonIQ-10k) — MLX
No-reference image-quality head on SigLIP2-SO400M for Apple Silicon (MLX). Independent from-paper reproduction of arXiv:2509.17374 — no upstream code/weights were released. The first MLX no-reference IQA head.
Ships the trained LoRA(q/k) + 3-layer MLP head adapter (~5 MB); the SigLIP2-SO400M backbone loads from the Google release at runtime.
Results (KonIQ-10k, 80/20 val)
SRCC 0.9575 · PLCC 0.9678 (paper reports SRCC ~0.932). Higher = better quality.
Usage
from siglip2_nriqa_mlx.score import NRIQAScorer
scorer = NRIQAScorer.from_pretrained("adapter.safetensors") # backbone auto-loaded
print(scorer.score("photo.jpg")) # ~0-100 MOS scale
Apache-2.0 (backbone Apache-2.0, Google). Training data KonIQ-10k is research-use — validate
licensing for commercial deployment. See NOTICE.
- Task
- Image Classification
- Library
- mlx
- License
- apache-2.0
- Created
- Jun 6, 2026
- Updated
- Jun 6, 2026