GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
MirroS-Lab
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
MirroS-Lab
Model Tree
Qwen/Qwen3.5-4B
Input Modalities
Output Modalities
Supported Functionality
The checkpoint can be served with vLLM:
bash
pip install "vllm==0.19.1" "transformers==5.11.0" qwen-vl-utils vllm serve MirroS-Lab/Code-as-World-VL-4B \ --served-model-name code-as-world-4b \ --max-model-len 4608 \ --gpu-memory-utilization 0.90 \ --media-io-kwargs '{"video":{"num_frames":16,"fps":-1,"video_backend":"openpangu"}}' \ --mm-processor-kwargs '{"do_sample_frames":false}' \ --mm-processor-cache-gb 0 \ --generation-config vllmThe server exposes an OpenAI-compatible API at /v1.
This model is intended for research on physical understanding, measurement, and quantitative reasoning from images and videos. Model outputs may be inaccurate and should be independently verified before use in safety-critical settings.
This checkpoint is released under the Apache License 2.0. It is derived from Qwen/Qwen3.5-4B; users must also comply with the terms applicable to the base model and their input data.
bibtex
@article{mirros2026codeasworld, title = {Code as Worlds: Agentic Discovery of Executable World Representations for Physical Reasoning}, author = {{MirroS Team}}, journal = {arXiv preprint arXiv:2608.27549}, year = {2026}}