GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
armand0e
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
armand0e
Model Tree
Qwen/Qwen3.5-2B
Input Modalities
Output Modalities
Supported Functionality
Base model: Qwen/Qwen3.5-2B
Adapter merged into base: armand0e/qwen3.5-2b-opus-repair-stage2-lora
Merged repo: armand0e/qwen3.5-2b-opus-repair-stage2-merged-16bit
Stage: stage2-step-sft
Stage purpose: Next-action SFT on sliced trajectories.
Adapter source: armand0e/qwen3.5-2b-opus-repair-stage2-lora
Stage data file: data/assembled/sft_qwen_next_actions_chat_repair.jsonl
The exact merge command and package versions are recorded in merge_config.json.