GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
AutomatosX
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
AutomatosX
Model Tree
mlx-community/Qwen3.5-0.8B-decision
Input Modalities
Output Modalities
Supported Functionality
This checkpoint scores a joint schema head. It is not a chat model. joint_head.safetensors is the original BF16 head, copied unchanged, with joint_head_config.json and decision_config.json. Text generation does not run that head.
Vision, MTP, norms, and token embeddings stay at source precision. This package is development evidence. It does not claim the upstream OptiQ decision scores, MTP acceleration, or parity with the BF16 checkpoint.
The upstream license is Apache-2.0. See LICENSE and NOTICE.