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 |
| Q5_K_M-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-Remix_Double-Quantization_Suite