GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
BaranH
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
BaranH
Model Tree
lightonai/LightOnOCR-3-4B
Input Modalities
Output Modalities
Supported Functionality
bash
pip install mlx-lmpython
from mlx_lm import load, generate model, tokenizer = load("BaranH/LightOnOCR-3-4B-mlx-8Bit") prompt="hello" if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None: messages = [{"role": "user", "content": prompt}] prompt = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) response = generate(model, tokenizer, prompt=prompt, verbose=True)