Modelpublic

Soulfate24/PaddleOCR-VL-1.6-ASHQ1-Remix-GGUF

sourceHugging Faceapache-2.0updated 16d agoView on Hugging Face

0likes1.1kdownloads

Model Card

PaddleOCR-VL-1.6 - ASHQ1-Remix

This is a GGUF quantized version of the original model.

📈 Release Benchmarks (wiki.test.raw, symmetric FA-auto reference)

Model	Size	PPL	KLD	RMS Δp	top-p	Speed
Q8_0 (stock)	475 MiB	544.1185	0.0178	1.67%	91.6%	7314 t/s
Fidelity-48pc 🥈	430 MiB	556.6220	0.0650	2.94%	87.0%	7314 t/s
Precision-42pc	392 MiB	522.0295†	0.0686	3.56%	83.4%	7314 t/s
Q6_K-imx (stock)	367 MiB	522.3200†	0.0694	3.57%	83.2%	7314 t/s
Quality-36pc	326 MiB	604.4922	0.1388	4.57%	76.6%	6400 t/s
Q5KM-imx (stock)	326 MiB	604.4922	0.1388	4.57%	76.6%	7314 t/s
IQ4_XS-imx (stock)	269 MiB	606.9490	0.5280	9.29%	61.8%	6400 t/s
IQ3_M-imx (stock)	239 MiB	768.5256	1.0750	14.12%	47.4%	6400 t/s

ℹ️ About ASHQ1-Remix Suite

Activation-aware GGUF quantization whose every ratio, floor, and cap traces to a measured experiment. Plain-BF16-native first; AutoRound lineage supported with explicit saturation bounds. Full seven-tier ladder validated across six model families.

🔗 Link: https://huggingface.co/Soulfate24/AutoRound-ASHQ1-RemixDouble-QuantizationSuite