GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
OX-PIXL
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
OX-PIXL
Model Tree
Input Modalities
Output Modalities
Supported Functionality
Use the following template for inference:
text
You FIRST observe the image in <observe> </observe> tags, then visualise the relevant scene graph in <scene> </scene> tags, followed by thinking about the reasoning process as an internal monologue within <think> </think> tags and then provide the final answer. The final answer MUST BE put within <answer> </answer> tags, and only return the final choice including the correct option and answer within the answer tags, e.g., <answer> (A) cat </answer>. Image size: {Width} x {Height}python
from transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessorfrom PIL import Image model = Qwen2_5_VLForConditionalGeneration.from_pretrained( "OX-PIXL/SpatialThinker-7B", torch_dtype="auto", device_map="auto")processor = AutoProcessor.from_pretrained("OX-PIXL/SpatialThinker-7B") # Load imageimage = Image.open("your_image.jpg")width, height = image.size # Prepare prompt with templatetemplate = f"""You FIRST observe the image in <observe> </observe> tags, then visualise the relevant scene graph in <scene> </scene> tags, followed by thinking about the reasoning process as an internal monologue within <think> </think> tags and then provide the final answer. The final answer MUST BE put within <answer> </answer> tags, and only return the final choice including the correct option and answer within the answer tags, e.g., <answer> (A) cat </answer>. Image size: {width} x {height}""" question = "Where is the cat relative to the couch? (A) on top of (B) in front of (C) behind (D) beside" messages = [ { "role": "user", "content": [ {"type": "image", "image": image}, {"type": "text", "text": template + "\n\n" + question}, ], }] text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = processor(text=[text], images=[image], return_tensors="pt").to(model.device) generated_ids = model.generate(**inputs, max_new_tokens=1024)output = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]print(output)bibtex
@misc{batra2025spatialthinkerreinforcing3dreasoning, title={SpatialThinker: Reinforcing 3D Reasoning in Multimodal LLMs via Spatial Rewards}, author={Hunar Batra and Haoqin Tu and Hardy Chen and Yuanze Lin and Cihang Xie and Ronald Clark}, year={2025}, eprint={2511.07403}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/2511.07403}, }You FIRST observe the image in <observe> </observe> tags, then visualise the relevant scene graph in <scene> </scene> tags, followed by thinking about the reasoning process as an internal monologue within <think> </think> tags and then provide the final answer. The final answer MUST BE put within <answer> </answer> tags, and only return the final choice including the correct option and answer within the answer tags, e.g., <answer> (A) cat </answer>.Image size: {Width} x {Height}from transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessorfrom PIL import Image model = Qwen2_5_VLForConditionalGeneration.from_pretrained( "OX-PIXL/SpatialThinker-7B", torch_dtype="auto", device_map="auto")processor = AutoProcessor.from_pretrained("OX-PIXL/SpatialThinker-7B") # Load imageimage = Image.open("your_image.jpg")width, height = image.size # Prepare prompt with templatetemplate = f"""You FIRST observe the image in <observe> </observe> tags, then visualise the relevant scene graph in <scene> </scene> tags, followed by thinking about the reasoning process as an internal monologue within <think> </think> tags and then provide the final answer. The final answer MUST BE put within <answer> </answer> tags, and only return the final choice including the correct option and answer within the answer tags, e.g., <answer> (A) cat </answer>. Image size: {width} x {height}""" question = "Where is the cat relative to the couch? (A) on top of (B) in front of (C) behind (D) beside" messages = [ { "role": "user", "content": [ {"type": "image", "image": image}, {"type": "text", "text": template + "\n\n" + question}, ], }] text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = processor(text=[text], images=[image], return_tensors="pt").to(model.device) generated_ids = model.generate(**inputs, max_new_tokens=1024)output = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]print(output)@misc{batra2025spatialthinkerreinforcing3dreasoning, title={SpatialThinker: Reinforcing 3D Reasoning in Multimodal LLMs via Spatial Rewards}, author={Hunar Batra and Haoqin Tu and Hardy Chen and Yuanze Lin and Cihang Xie and Ronald Clark}, year={2025}, eprint={2511.07403}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/2511.07403}, }