GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
LSW142857
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
LSW142857
Model Tree
Qwen/Qwen3.5-9B
Input Modalities
Output Modalities
Supported Functionality
bash
hf download LSW142857/Qwen3.5-9B-OPSD-PI-Medium-ckpt23 \--repo-type model \--local-dir Qwen3.5-9B-OPSD-PI-Medium-ckpt23
The four safetensors shards contain the complete base model plus the merged adapter, so no separate base-model download is required. The model is intended for text coding-agent evaluation. The training-time standalone MTP parameters are not part of the LoRA-only adapter; use target-model decoding (speculative decoding disabled) for the reported evaluation contract.
See MERGED_MODEL_MANIFEST.json for checkpoint provenance and shard checksums.