GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
YasserSami
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
YasserSami
Model Tree
Qwen/Qwen3-VL-4B-Instruct
Input Modalities
Output Modalities
Supported Functionality
| Model | CER ↓ | WER ↓ | BLEU ↑ |
|---|---|---|---|
| Qari-OCR-0.4.0 | 0.1222 | 0.2562 | 68.41 |
| Qwen/Qwen3-VL-4B-Instruct | 0.4922 | 0.6966 | 34.61 |
| Qwen/Qwen3-VL-8B-Instruct | 0.6876 | 0.8954 | 23.89 |
| NAMAA/Qari-0.2.2.1 | 0.6448 | 0.5126 | 21.97 |
| MBZUAI/AIN | 1.2843 | 1.2697 | 3.50 |
python
from transformers import AutoProcessor, AutoModelForVision2Seqfrom PIL import Imageimport torch model_name = "NAMAA-Space/Qari-OCR-0.4.0-VL-4B-Instruct"processor = AutoProcessor.from_pretrained(model_name)model = AutoModelForVision2Seq.from_pretrained( model_name, torch_dtype=torch.float16, device_map="auto") messages = [ { "role": "user", "content": [ {"type": "image", "image": f"./{src}"}, {"type": "text", "text": "Free OCR."}, ], }] # Preparation for inferenceinputs = processor.apply_chat_template( messages, tokenize=True, add_generation_prompt=True, return_dict=True, return_tensors="pt")inputs = inputs.to(model.device) # Inference: Generation of the outputgenerated_ids = model.generate(**inputs, max_new_tokens=2048)generated_ids_trimmed = [ out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]result = processor.batch_decode( generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]bibtex
@misc{qari-ocr-0.4.0, author = {NAMAA-Space}, title = {Qari-OCR-0.4.0-VL-4B-Instruct}, year = {2025}, publisher = {HuggingFace}, howpublished = {\url{https://huggingface.co/NAMAA-Space/Qari-OCR-0.4.0-VL-4B-Instruct}}}from transformers import AutoProcessor, AutoModelForVision2Seqfrom PIL import Imageimport torch model_name = "NAMAA-Space/Qari-OCR-0.4.0-VL-4B-Instruct"processor = AutoProcessor.from_pretrained(model_name)model = AutoModelForVision2Seq.from_pretrained( model_name, torch_dtype=torch.float16, device_map="auto") messages = [ { "role": "user", "content": [ {"type": "image", "image": f"./{src}"}, {"type": "text", "text": "Free OCR."}, ], }] # Preparation for inferenceinputs = processor.apply_chat_template( messages, tokenize=True, add_generation_prompt=True, return_dict=True, return_tensors="pt")inputs = inputs.to(model.device) # Inference: Generation of the outputgenerated_ids = model.generate(**inputs, max_new_tokens=2048)generated_ids_trimmed = [ out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]result = processor.batch_decode( generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]@misc{qari-ocr-0.4.0, author = {NAMAA-Space}, title = {Qari-OCR-0.4.0-VL-4B-Instruct}, year = {2025}, publisher = {HuggingFace}, howpublished = {\url{https://huggingface.co/NAMAA-Space/Qari-OCR-0.4.0-VL-4B-Instruct}}}