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
Cloudflare/clef-omni
Input Modalities
Output Modalities
Supported Functionality
Clef-Omni is not a chat model. A request is a state plus a schema of typed questions (noul, choice, score). One prefill returns a probability for every allowed option. joint_head.safetensors is the original BF16 joint schema head, copied unchanged, with joint_schema_model.py and joint_head_config.json. Text generation does not run that head. Upstream load_release_model does not load the talker or code2wav, and it does not load this NVFP4 checkpoint.
Vision, the audio encoder, code2wav, norms, token embeddings, and the LM heads stay at source precision. Talker experts are quantized with the thinker trunk. Speech output was not measured. The joint schema head is not part of the language index and is not quantized. This package is development evidence. It is not a Decision Index certificate, and it does not claim parity with the upstream BF16 checkpoint. No CUDA decision-head forward was run.
The upstream license is Apache-2.0. See LICENSE and NOTICE.