Melaraby/qwen_vlm_arabic_ocr-GGUF

qwenvlmarabic_ocr — GGUF bundle for LM Studio

Vision (OCR) model. LM Studio needs BOTH of these in the SAME folder (it pairs them automatically by the mmproj filename prefix):

• —Language model(s): qwenvlmarabic_ocr-F16.gguf
• —Vision projector : mmproj-qwenvlmarabic_ocr-F16.gguf

Quantization is optional for a model this small — the F16 file works directly in LM Studio (~1.6 GB) and needs no compiled llama.cpp. Any *-Q4_K_M/*-Q8_0 files present were quantized with a llama-quantize binary.

Load in LM Studio

1. 1.Copy this whole folder into your LM Studio models directory: macOS/Linux : ~/.lmstudio/models/Melaraby/qwenvlmarabicocr/ Windows : %USERPROFILE%\.lmstudio\models\Melaraby\qwenvlmarabicocr\
2. 2.Rescan models. A vision ("eye") icon = the mmproj was detected.
3. 3.Attach an image and use the trained OCR prompt: System: You are an OCR engine. Detect every text line and output <|boxstart|>(ymin,xmin,ymax,xmax)<|boxend|>transcribed text User : (image) + "Transcribe all text lines."

Sanity check with llama.cpp directly

llama-mtmd-cli -m qwenvlmarabicocr-F16.gguf --mmproj mmproj-qwenvlmarabicocr-F16.gguf --image page.jpg -p "Transcribe all text lines."