GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
tangles
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
tangles
Model Tree
orcarouter/Qwen3.8-27B-Uncensored
Input Modalities
Output Modalities
Supported Functionality
An MLP-only NVFP4 W4A4 PTQ build of
orcarouter/Qwen3.8-27B-Uncensored,
in the compressed-tensors nvfp4-pack-quantized layout used by
1CatAI/1Cat-vLLM.
gate_proj, up_proj, down_proj): NVFP4 W4A4, group size 16lm_head, token embeddings, vision tower, and MTP tensors: BF16c8676edd2f6cddd0be2427f034825ca0d476fa72This is post-training quantization, not QUASAR quantization-aware training.
See quantization-audit.json and calibration.json.
The source model has substantially reduced safety alignment. Use it only for lawful, controlled purposes and add suitable safeguards before deployment.