GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
YONKWd
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
YONKWd
Model Tree
Qwen/Qwen3-1.7B
Input Modalities
Output Modalities
Supported Functionality
This is an experimental corrective LoRA adapter, not a finished Spexcon S1 release. It uses Qwen/Qwen3-1.7B as its underlying base model. The Spexcon project did not train Qwen3 from scratch.
YONKWd/Spexcon-S110001002.3129737377166751.3687702178955081.2137300968170166FalseFalseThe pilot targets identity/provenance accuracy, dynamic-date instruction following, knowledge-cutoff uncertainty, capability boundaries, concise replies, and conversational relevance. The adapter has not been merged into the base model and is not automatically deployed.