GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
hudsongouge
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
hudsongouge
Model Tree
Qwen/Qwen3.5-4B
Input Modalities
Output Modalities
Supported Functionality
Podcast transcript cleaning (think → JSON). For fast local serving, prefer the merged NVFP4 export used in this workspace (models/Qwen3.5-4B-NVFP4-podcast-cleaner), not this adapter alone.
python
from peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizerbase = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-4B", torch_dtype="bfloat16", device_map="auto")tok = AutoTokenizer.from_pretrained("Qwen/Qwen3.5-4B")model = PeftModel.from_pretrained(base, "hudsongouge/qwen35-4b-g2d-dpo")
outputs/qwen35-4b-g2d-* in the Fine-Tune-Experiments workspace