GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
VLR-CVC
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
VLR-CVC
Model Tree
Qwen/Qwen3.5-2B-Base
Input Modalities
Output Modalities
Supported Functionality
Two supervised finetuning stages, both at sequence length 16384 on 64 nodes of JUPITER (4x GH200 per node):
Learning rate 1e-5 for the decoder and projector, 1e-6 for the vision encoder, 100 warmup steps. Images are capped at 1024px on the long side.
<think> blocks on every assistant turn rather than only the
last, matching how the model was trained.eos_token is <|im_end|>, and generation_config.json stops on both
<|im_end|> (248046) and <|endoftext|> (248044).