Soulfate24/OvisOCR2-ASHQ1-Remix-GGUF overview
OvisOCR2 ASHQ1 Remix This is a GGUF quantized version of the original model. ๐ Release Benchmarks wiki.test.raw, symmetric FA auto reference | Model | Size | โฆ
Runs locally from ~1.1 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| imatrix.gguf | GGUF | GGUF | 1.1 MB | Download |
| mmproj-ASHQ1-Balanced-54pc.gguf | GGUF | GGUF | 121.8 MB | Download |
| model-ASHQ1-Fidelity-48pc.gguf | GGUF | GGUF | 704.5 MB | Download |
| model-ASHQ1-Nano-27pc.gguf | GGUF | GGUF | 457.0 MB | Download |
| model-ASHQ1-Pico-24pc.gguf | GGUF | GGUF | 441.8 MB | Download |
| model-ASHQ1-Precision-42pc.gguf | GGUF | GGUF | 669.6 MB | Download |
| model-ASHQ1-Quality-36pc.gguf | GGUF | GGUF | 556.2 MB | Download |
Model Details
| Model ID | Soulfate24/OvisOCR2-ASHQ1-Remix-GGUF |
|---|---|
| Author | Soulfate24 |
| Pipeline | image-text-to-text |
| License | apache-2.0 |
| Base model | ATH-MaaS/OvisOCR2 |
| Last modified | 2026-09-10T10:39:42.000Z |
Model README
---
license: apache-2.0
library_name: transformers
pipeline_tag: image-text-to-text
base_model:
- ATH-MaaS/OvisOCR2
tags:
- ocr
- document-parsing
- multimodal
- markdown
- tables
- formulas
- vllm
- qwen3_5
- quantization
- gguf
- ashq1
- imatrix
---
OvisOCR2 - 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) | 774 MiB | 28.7134 | 0.0009 | 0.61% | 98.3% | 3413 t/s |
| Fidelity-48pc | 704 MiB | 28.7754 | 0.0019 | 0.96% | 97.3% | 2560 t/s |
| Precision-42pc ๐ฅ | 670 MiB | 28.8111 | 0.0023 | 1.04% | 97.2% | 3200 t/s |
| Q6_K-imx (stock) | 601 MiB | 28.8894 | 0.0033 | 1.25% | 96.5% | 3413 t/s |
| Quality-36pc โญ | 556 MiB | 29.0026 | 0.0077 | 1.93% | 94.7% | 3200 t/s |
| Q5_K_M-imx (stock) | 551 MiB | 29.0602 | 0.0088 | 2.02% | 94.2% | 3200 t/s |
| IQ4_XS-imx (stock) | 481 MiB | 30.5363 | 0.0305 | 3.94% | 90.2% | 3413 t/s |
| Nano-27pc | 457 MiB | 30.5109 | 0.0598 | 5.82% | 87.2% | 3200 t/s |
| Pico-24pc | 442 MiB | 31.9258 | 0.0699 | 6.16% | 85.6% | 3200 t/s |
| IQ3_M-imx (stock) | 433 MiB | 32.0551 | 0.0895 | 7.35% | 84.2% | 3200 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/OvisOCR2-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