GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Offensive-AI-Lab
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
Offensive-AI-Lab
Model Tree
Qwen/Qwen3.5-9B
Input Modalities
Output Modalities
Supported Functionality
| File | SHA-256 |
|---|---|
adapter_config.json | b049c48d32dfbb25e605949b6859dbe2eb53bd680d36eb6171f82e97003306cc |
adapter_model.safetensors | 1830598a70e652d4bf5a39de4439d7683e8e5825cc5c053b66cdcbbe187e1612 |
The supported integration is the comparison mode in the
prism demo:
bash
git clone https://github.com/Offensive-AI-Lab/prismcd prismuv sync --extra demouv run python scripts/download_baselines.py --only aouv run python demo/app.py
The adapter files are licensed under Apache-2.0. They do not include Qwen3.5-9B weights. The adapted Activation Oracles implementation is MIT, Copyright (c) 2025 Adam Karvonen, and is attributed in the PRISM repository.