GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
eewer
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
eewer
Model Tree
Qwen/Qwen3.5-4B
Input Modalities
Output Modalities
Supported Functionality
Derived from Qwen/Qwen3.5-4B with a single change to the chat template:
<think>...</think> reasoning, not just the latest one.<think>; passing
enable_thinking=False has no effect.This makes multi-turn agent training match evaluation (the model always sees its own prior reasoning). Model weights are identical to Qwen3.5-4B; only the chat template differs. Vision weights are unchanged (not trained in the terminal-agent recipes).