GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
quangbin
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
quangbin
Model Tree
Input Modalities
Output Modalities
Supported Functionality
safetensors weight shards;model.safetensors.index.json;The weight shards contain 66,714,912,784 bytes. Their expected filenames,
byte sizes, and SHA-256 checksums are provided in the review artifact's
CHECKPOINT_WEIGHTS_MANIFEST.tsv and CHECKPOINT_WEIGHTS.sha256 files.
This checkpoint supports inspection and evaluation together with the separate anonymous inference/evaluation code snapshot. Synthetic-task generation, training, and production orchestration infrastructure are not included, so this artifact does not reproduce the full training pipeline.