GraySoft
Projects Models Compare Cloud benchmarks FAQ Download guIDE →
Model Intelligence Sheet

cstr/qari-ocr-crispembed-GGUF overview

Qari OCR CrispEmbed GGUF GGUF conversion of NAMAA Space/Qari OCR 0.2.2.1 VL 2B Instruct https://huggingface.co/NAMAA Space/Qari OCR 0.2.2.1 VL 2B Instruct Apac…

ggufocrarabiccrispembedqwen2-vlimage-text-to-textarbase_model:NAMAA-Space/Qari-OCR-0.2.2.1-VL-2B-Instructbase_model:quantized:NAMAA-Space/Qari-OCR-0.2.2.1-VL-2B-Instructlicense:apache-2.0region:us

Runs locally from ~5.3 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads
572
Likes
0
Pipeline
image-text-to-text
Author

Repository Files & Downloads

5 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
diff-harness-ref/qari-ocr-ref.ggufGGUFGGUF5.3 MBDownload
qari-ocr-2b-f16.ggufGGUFF164.56 GBDownload
qari-ocr-2b-q4_k.ggufGGUFQ4_K1.61 GBDownload
qari-ocr-2b-q8_0.ggufGGUFQ8_02.22 GBDownload
qari-ocr-ref.ggufGGUFGGUF5.3 MBDownload

Model Details

Model IDcstr/qari-ocr-crispembed-GGUF
Authorcstr
Pipelineimage-text-to-text
Licenseapache-2.0
Base modelNAMAA-Space/Qari-OCR-0.2.2.1-VL-2B-Instruct
Last modified2026-06-21T06:23:08.000Z

Model README

---

license: apache-2.0

tags:

- ocr

- arabic

- gguf

- crispembed

- qwen2-vl

base_model: NAMAA-Space/Qari-OCR-0.2.2.1-VL-2B-Instruct

language: ar

pipeline_tag: image-text-to-text

---

Qari-OCR CrispEmbed GGUF

GGUF conversion of NAMAA-Space/Qari-OCR-0.2.2.1-VL-2B-Instruct (Apache-2.0) for use with CrispEmbed.

Model

Arabic OCR with full diacritics (tashkeel) support. Fine-tuned from Qwen2-VL-2B-Instruct via LoRA (r=16, alpha=16, 324 adapter pairs) on 50K Arabic OCR samples.

  • Architecture: Qwen2-VL-2B (32L ViT 1280d + spatial merger + 28L Qwen2 LLM 1536d, GQA 12/2)
  • Parameters: 2B
  • Performance: WER=0.221, CER=0.059, BLEU=0.597
  • Training: 50K Arabic OCR records, 1 epoch, LoRA on attention+MLP

Files

| File | Type | Size |

|------|------|------|

| qari-ocr-2b-f16.gguf | F16 | 4.7 GB |

| qari-ocr-2b-q8_0.gguf | Q8_0 | 2.3 GB |

| qari-ocr-2b-q4_k.gguf | Q4_K | 1.6 GB |

Usage

Uses the same qwen2vl engine as other Qwen2-VL models in CrispEmbed.

Conversion

LoRA adapter merged into full-precision Qwen2-VL-2B-Instruct base weights (324 pairs, tensor-by-tensor), then converted to GGUF via CrispEmbed converter. Quantized with crispembed-quantize (vision weights at Q8_0 floor).

License

Apache-2.0 (NAMAA-Space/Qari-OCR).

Run cstr/qari-ocr-crispembed-GGUF with guIDE

Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.

Download guIDE → · Browse 524k+ models · Compare models

Source: Hugging Face · Compare models