GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
trillionlabs
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
trillionlabs
Model Tree
Qwen/Qwen3-VL-8B-Instruct
Input Modalities
Output Modalities
Supported Functionality
You can run inference using the vLLM library as follows:
python
from vllm import LLM, SamplingParamsfrom transformers import AutoProcessorfrom PIL import Image # Model configuration (choose one)# For gWorld-8B:MODEL_PATH = "trillionlabs/gWorld-8B"BASE_MODEL = "Qwen/Qwen3-VL-8B-Instruct" # For gWorld-32B:# MODEL_PATH = "trillionlabs/gWorld-32B"# BASE_MODEL = "Qwen/Qwen3-VL-32B" # Image processing settingsMM_PROCESSOR_KWARGS = { "max_pixels": 4233600, "min_pixels": 3136,} # Load modelllm = LLM( model=MODEL_PATH, tokenizer=BASE_MODEL, tensor_parallel_size=8, gpu_memory_utilization=0.9, max_model_len=19384, trust_remote_code=True, mm_processor_kwargs=MM_PROCESSOR_KWARGS, enable_chunked_prefill=True, max_num_batched_tokens=16384,) # Load processor for chat templateprocessor = AutoProcessor.from_pretrained(BASE_MODEL, trust_remote_code=True) # Prepare inputimage = Image.open("screenshot.png")if image.mode != 'RGB': image = image.convert('RGB') action = '{"action_type": "TAP", "coordinates": [512, 890]}' # World model prompt templateuser_content = f"""You are an expert mobile UI World Model that can accurately predict the next state given an action.Given a screenshot of a mobile interface and an action, you must generate clean, responsive HTML code that represents the state of the interface AFTER the action is performed.First generate reasoning about what the next state should look like based on the action.Afterwards, generate the HTML code representing the next state that logically follows the action.You will render this HTML in a mobile viewport to see how similar it looks and acts like the mobile screenshot. Requirements:1. Provide reasoning about what the next state should look like based on the action2. Generate complete, valid HTML5 code3. Choose between using inline CSS and utility classes from Bootstrap, Tailwind CSS, or MUI for styling, depending on which option generates the closest code to the screenshot.4. Use mobile-first design principles matching screenshot dimensions.5. For images, use inline SVG placeholders with explicit width and height attributes that match the approximate dimensions from the screenshot. Matching the approximate color is also good.6. Use modern web standards and best practices7. Return ONLY the HTML code, no explanations or markdown formatting8. The generated HTML should render properly in a mobile viewport.9. Generated HTML should look like the screen that logically follows the current screen and the action. Action:{action} Output format:# Next State Reasoning: <your reasoning about what the next state should look like># HTML: <valid_html_code> Generate the next state reasoning and the next state in html:""" # Build messagesmessages = [ { "role": "user", "content": [ {"type": "image", "image": image}, {"type": "text", "text": user_content}, ], }] # Apply chat templateprompt = processor.apply_chat_template( messages, tokenize=False, add_generation_prompt=True,) # Generation parameterssampling_params = SamplingParams( max_tokens=15000, temperature=0, seed=42, top_p=1.0,) # Generateoutputs = llm.generate( [{"prompt": prompt, "multi_modal_data": {"image": image}}], sampling_params=sampling_params) print(outputs[0].outputs[0].text)Qwen3-VL-8BgWorld-8B establishes a new Pareto frontier in the trade-off between model size and GUI world modeling accuracy.
Llama 4 402B-A17B) on GUI-specific benchmarks.The model treats the mobile interface as a coordinate space and predicts how that space changes based on user input.
{"action_type": "TAP", "coordinates": [512, 890]} or {"action_type": "TYPE", "text": "gWorld is a generative code mobile world model"}By outputting HTML/CSS, gWorld ensures that text remains perfectly sharp and layouts are responsive.
This model is licensed under the Apache License 2.0. For inquiries, please contact: info@trillionlabs.co
bibtex
@inproceedings{koh2026gworld, title = {Generative Visual Code Mobile World Models}, author = {Koh, Woosung and Han, Sungjun and Lee, Segyu and Yun, Se-Young and Shin, Jamin}, booktitle = {International Conference on Machine Learning (ICML)}, year = {2026}, note = {arXiv:2602.01576}}from vllm import LLM, SamplingParamsfrom transformers import AutoProcessorfrom PIL import Image # Model configuration (choose one)# For gWorld-8B:MODEL_PATH = "trillionlabs/gWorld-8B"BASE_MODEL = "Qwen/Qwen3-VL-8B-Instruct" # For gWorld-32B:# MODEL_PATH = "trillionlabs/gWorld-32B"# BASE_MODEL = "Qwen/Qwen3-VL-32B" # Image processing settingsMM_PROCESSOR_KWARGS = { "max_pixels": 4233600, "min_pixels": 3136,} # Load modelllm = LLM( model=MODEL_PATH, tokenizer=BASE_MODEL, tensor_parallel_size=8, gpu_memory_utilization=0.9, max_model_len=19384, trust_remote_code=True, mm_processor_kwargs=MM_PROCESSOR_KWARGS, enable_chunked_prefill=True, max_num_batched_tokens=16384,) # Load processor for chat templateprocessor = AutoProcessor.from_pretrained(BASE_MODEL, trust_remote_code=True) # Prepare inputimage = Image.open("screenshot.png")if image.mode != 'RGB': image = image.convert('RGB') action = '{"action_type": "TAP", "coordinates": [512, 890]}' # World model prompt templateuser_content = f"""You are an expert mobile UI World Model that can accurately predict the next state given an action.Given a screenshot of a mobile interface and an action, you must generate clean, responsive HTML code that represents the state of the interface AFTER the action is performed.First generate reasoning about what the next state should look like based on the action.Afterwards, generate the HTML code representing the next state that logically follows the action.You will render this HTML in a mobile viewport to see how similar it looks and acts like the mobile screenshot. Requirements:1. Provide reasoning about what the next state should look like based on the action2. Generate complete, valid HTML5 code3. Choose between using inline CSS and utility classes from Bootstrap, Tailwind CSS, or MUI for styling, depending on which option generates the closest code to the screenshot.4. Use mobile-first design principles matching screenshot dimensions.5. For images, use inline SVG placeholders with explicit width and height attributes that match the approximate dimensions from the screenshot. Matching the approximate color is also good.6. Use modern web standards and best practices7. Return ONLY the HTML code, no explanations or markdown formatting8. The generated HTML should render properly in a mobile viewport.9. Generated HTML should look like the screen that logically follows the current screen and the action. Action:{action} Output format:# Next State Reasoning: <your reasoning about what the next state should look like># HTML: <valid_html_code> Generate the next state reasoning and the next state in html:""" # Build messagesmessages = [ { "role": "user", "content": [ {"type": "image", "image": image}, {"type": "text", "text": user_content}, ], }] # Apply chat templateprompt = processor.apply_chat_template( messages, tokenize=False, add_generation_prompt=True,) # Generation parameterssampling_params = SamplingParams( max_tokens=15000, temperature=0, seed=42, top_p=1.0,) # Generateoutputs = llm.generate( [{"prompt": prompt, "multi_modal_data": {"image": image}}], sampling_params=sampling_params) print(outputs[0].outputs[0].text)@inproceedings{koh2026gworld, title = {Generative Visual Code Mobile World Models}, author = {Koh, Woosung and Han, Sungjun and Lee, Segyu and Yun, Se-Young and Shin, Jamin}, booktitle = {International Conference on Machine Learning (ICML)}, year = {2026}, note = {arXiv:2602.01576}}