GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
KATHIR2006
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
KATHIR2006
Model Tree
HuggingFaceTB/SmolVLM-Instruct
Input Modalities
Output Modalities
Supported Functionality
Zenthi-AI functions as an orchestrator that dynamically routes user queries to specialized model experts depending on request characteristics:
riven/smolvlm:latest (~545 MB)qwen2.5:1.5b-instruct (~986 MB)qwen2.5-coder:3b (~1.9 GB)The base Qwen2.5-0.5B-Instruct model was fine-tuned using QLoRA (4-bit quantization) on a curated blend of several high-quality datasets:
This model is fully compliant with the Apache 2.0 License in accordance with its base Qwen2.5 model guidelines. You are free to modify, distribute, and utilize this model for commercial or non-commercial applications.