GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
6cf
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
6cf
Model Tree
Qwen/Qwen3.5-4B
Input Modalities
Output Modalities
Supported Functionality
The checkpoint uses the native Qwen3.5 XML tool-call format. A typical call has the following shape:
markdown
<tool_call><function=Read><parameter=file_path>/testbed/package/module.py</parameter></function></tool_call>
Do not convert this checkpoint to a legacy Hermes JSON tool-call template at inference time. Use the included tokenizer and chat_template.jinja.
Tool outputs and environment responses were retained as conversation context but were not intended as model-generated supervision. The supervised targets are assistant turns, including native Qwen3.5 tool calls and final responses.
Use a recent Transformers release with Qwen3.5 support.
markdown
from transformers import AutoModelForImageTextToText, AutoProcessormodel_id = "6cf/Qwen3.5-4B-SWE-SFT-Coldstart"processor = AutoProcessor.from_pretrained(model_id,trust_remote_code=True,)model = AutoModelForImageTextToText.from_pretrained(model_id,torch_dtype="auto",device_map="auto",trust_remote_code=True,)
For text-only agent inference, the same processor and model can be used with a text conversation and tool schemas passed through the included chat template.