Soulfate24/PaddleOCR-VL-1.6-ASHQ1-Remix-GGUF overview
PaddleOCR VL 1.6 ASHQ1 Remix This is a GGUF quantized version of the original model. ๐ Release Benchmarks wiki.test.raw, symmetric FA auto reference | Model |โฆ
Runs locally from ~0.7 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| imatrix.gguf | GGUF | GGUF | 0.7 MB | Download |
| mmproj-ASHQ1-Balanced-72pc.gguf | GGUF | GGUF | 593.1 MB | Download |
| model-ASHQ1-Fidelity-48pc.gguf | GGUF | GGUF | 430.2 MB | Download |
| model-ASHQ1-Precision-42pc.gguf | GGUF | GGUF | 391.9 MB | Download |
| model-ASHQ1-Quality-36pc.gguf | GGUF | GGUF | 325.7 MB | Download |
| model-Q8_0.gguf | GGUF | Q8_0 | 475.2 MB | Download |
Model Details
| Model ID | Soulfate24/PaddleOCR-VL-1.6-ASHQ1-Remix-GGUF |
|---|---|
| Author | Soulfate24 |
| Pipeline | image-text-to-text |
| License | apache-2.0 |
| Base model | PaddlePaddle/PaddleOCR-VL-1.6 |
| Last modified | 2026-09-11T07:44:36.000Z |
Model README
---
license: apache-2.0
pipeline_tag: image-text-to-text
language:
- en
- zh
- multilingual
library_name: PaddleOCR
base_model:
- PaddlePaddle/PaddleOCR-VL-1.6
tags:
- ERNIE4.5
- PaddleOCR
- PaddlePaddle
- image-to-text
- ocr
- document-parse
- layout
- table
- formula
- chart
- seal
- spotting
- quantization
- gguf
- ashq1
- imatrix
---
PaddleOCR-VL-1.6 - ASHQ1-Remix
This is a GGUF quantized version of the original model.
๐ Release Benchmarks (wiki.test.raw, symmetric FA-auto reference)
| Model | Size | PPL | KLD | RMS ฮp | top-p | Speed |
| :--- | ---: | ---: | ---: | ---: | ---: | ---: |
| Q8_0 (stock) | 475 MiB | 544.1185 | 0.0178 | 1.67% | 91.6% | 7314 t/s |
| Fidelity-48pc ๐ฅ | 430 MiB | 556.6220 | 0.0650 | 2.94% | 87.0% | 7314 t/s |
| Precision-42pc | 392 MiB | 522.0295โ | 0.0686 | 3.56% | 83.4% | 7314 t/s |
| Q6_K-imx (stock) | 367 MiB | 522.3200โ | 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 |
โน๏ธ 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.
๐ Link: https://huggingface.co/Soulfate24/AutoRound-ASHQ1-Remix_Double-Quantization_Suite
Run Soulfate24/PaddleOCR-VL-1.6-ASHQ1-Remix-GGUF with guIDE
Download guIDE โ the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face ยท Compare models