GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
NAMAA-Space
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
NAMAA-Space
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}}}